2025
Cao, Zhaoyang; Nguyen, John; Zafarani, Reza
Is Less Really More? Fake News Detection with Limited Information Journal Article
In: SIGKDD Explor. Newsl., vol. 27, no. 1, pp. 20–31, 2025, ISSN: 1931-0145.
@article{10.1145/3748239.3748243,
title = {Is Less Really More? Fake News Detection with Limited Information},
author = {Zhaoyang Cao and John Nguyen and Reza Zafarani},
url = {https://doi.org/10.1145/3748239.3748243},
doi = {10.1145/3748239.3748243},
issn = {1931-0145},
year = {2025},
date = {2025-07-01},
journal = {SIGKDD Explor. Newsl.},
volume = {27},
number = {1},
pages = {20–31},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {The threat that online fake news and misinformation pose to democracy, justice, public confidence, and especially to vulnerable populations has led to a sharp increase in the need for fake news detection and intervention. Whether multi-modal or pure text-based, most existing fake news detection methods depend on textual analysis of entire articles. However, these fake news detection methods come with certain limitations. For instance, fake news detection methods that rely on full text can be computationally inefficient, demand large amounts of training data to achieve competitive accuracy, and may lack robustness across different datasets. This is because fake news datasets have strong variations in terms of the level and types of information they provide; where some can include large paragraphs of text with images and metadata, and others can be a few short sentences. Perhaps if one could only use minimal information to detect fake news, fake news detection methods could become more robust and resilient to the lack of information. We aim to overcome these limitations by detecting fake news using systematically selected, limited information that is both effective and capable of delivering robust, promising performance. We propose a framework called SLIM (Systematically-selected Limited Information) for fake news detection. In SLIM, we quantify the amount of information by introducing information-theoretic measures. SLIM leverages limited information (e.g., a few named entities) to achieve performance in fake news detection comparable to that of state-of-the-art obtained using the full text, even when the dataset is sparse. Furthermore, by combining various types of limited information, SLIM can perform even better while significantly reducing the quantity of information required for training compared to state-of-the-art language model-based fake news detection techniques.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The threat that online fake news and misinformation pose to democracy, justice, public confidence, and especially to vulnerable populations has led to a sharp increase in the need for fake news detection and intervention. Whether multi-modal or pure text-based, most existing fake news detection methods depend on textual analysis of entire articles. However, these fake news detection methods come with certain limitations. For instance, fake news detection methods that rely on full text can be computationally inefficient, demand large amounts of training data to achieve competitive accuracy, and may lack robustness across different datasets. This is because fake news datasets have strong variations in terms of the level and types of information they provide; where some can include large paragraphs of text with images and metadata, and others can be a few short sentences. Perhaps if one could only use minimal information to detect fake news, fake news detection methods could become more robust and resilient to the lack of information. We aim to overcome these limitations by detecting fake news using systematically selected, limited information that is both effective and capable of delivering robust, promising performance. We propose a framework called SLIM (Systematically-selected Limited Information) for fake news detection. In SLIM, we quantify the amount of information by introducing information-theoretic measures. SLIM leverages limited information (e.g., a few named entities) to achieve performance in fake news detection comparable to that of state-of-the-art obtained using the full text, even when the dataset is sparse. Furthermore, by combining various types of limited information, SLIM can perform even better while significantly reducing the quantity of information required for training compared to state-of-the-art language model-based fake news detection techniques.
Tian, Hao; Jin, Shengmin; Zafarani, Reza
Representing Higher-Order Networks with Spectral Moments Proceedings Article
In: Proceedings of the The 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Sydney, Australia, 2025.
@inproceedings{spectralhigherorder,
title = {Representing Higher-Order Networks with Spectral Moments},
author = {Hao Tian and Shengmin Jin and Reza Zafarani},
year = {2025},
date = {2025-01-01},
booktitle = {Proceedings of the
The 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
publisher = {Association for Computing Machinery},
address = {Sydney, Australia},
series = {PAKDD '25},
abstract = {The spectral properties of traditional (dyadic) graphs, where an edge connects exactly two vertices, are widely utilized in different applications. These spectral properties are closely connected to the structural properties of dyadic graphs. We generalize such connections and characterize higher-order networks by their spectral information. We first split the higher-order graphs by their orders into several uniform hypergraphs. For each uniform hypergraph, we extract the corresponding spectral information from the transition matrices of carefully designed random walks. From each spectrum, we compute the first few spectral moments and use all such spectral moments across different orders as the higher-order graph representation. We will show that these moments not only clearly indicate the return probabilities of random walks but are also closely related to various higher-order network properties such as degree distribution and clustering coefficient. Extensive experiments show the utility of this new representation in various settings. For instance, graph classification on higher-order graphs shows that this representation significantly outperforms other techniques.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The spectral properties of traditional (dyadic) graphs, where an edge connects exactly two vertices, are widely utilized in different applications. These spectral properties are closely connected to the structural properties of dyadic graphs. We generalize such connections and characterize higher-order networks by their spectral information. We first split the higher-order graphs by their orders into several uniform hypergraphs. For each uniform hypergraph, we extract the corresponding spectral information from the transition matrices of carefully designed random walks. From each spectrum, we compute the first few spectral moments and use all such spectral moments across different orders as the higher-order graph representation. We will show that these moments not only clearly indicate the return probabilities of random walks but are also closely related to various higher-order network properties such as degree distribution and clustering coefficient. Extensive experiments show the utility of this new representation in various settings. For instance, graph classification on higher-order graphs shows that this representation significantly outperforms other techniques.
Cao, Zhaoyang; Schooler, Lael; Zafarani, Reza
Analyzing Memory Effects in Large Language Models through the lens of Cognitive Psychology Miscellaneous
2025.
@misc{cao2025analyzingmemoryeffectslarge,
title = {Analyzing Memory Effects in Large Language Models through the lens of Cognitive Psychology},
author = {Zhaoyang Cao and Lael Schooler and Reza Zafarani},
url = {https://arxiv.org/abs/2509.17138},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Cai, Weibin; Li, Jiayu; Zafarani, Reza
Unpacking Hateful Memes: Presupposed Context and False Claims Miscellaneous
2025.
@misc{cai2025unpackinghatefulmemespresupposed,
title = {Unpacking Hateful Memes: Presupposed Context and False Claims},
author = {Weibin Cai and Jiayu Li and Reza Zafarani},
url = {https://arxiv.org/abs/2510.09935},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Cai, Weibin; Zafarani, Reza
Seeing Hate Differently: Hate Subspace Modeling for Culture-Aware Hate Speech Detection Miscellaneous
2025.
@misc{cai2025seeinghatedifferentlyhate,
title = {Seeing Hate Differently: Hate Subspace Modeling for Culture-Aware Hate Speech Detection},
author = {Weibin Cai and Reza Zafarani},
url = {https://arxiv.org/abs/2510.13837},
year = {2025},
date = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
2024
Tian, Hao; Zafarani, Reza
Higher-Order Networks Representation and Learning: A Survey Journal Article
In: SIGKDD Explor. Newsl., vol. 26, no. 1, pp. 1–18, 2024, ISSN: 1931-0145.
@article{10.1145/3682112.3682114,
title = {Higher-Order Networks Representation and Learning: A Survey},
author = {Hao Tian and Reza Zafarani},
url = {https://doi.org/10.1145/3682112.3682114},
doi = {10.1145/3682112.3682114},
issn = {1931-0145},
year = {2024},
date = {2024-07-01},
journal = {SIGKDD Explor. Newsl.},
volume = {26},
number = {1},
pages = {1–18},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Network data has become widespread, larger, and more complex over the years. Traditional network data is dyadic, capturing the relations among pairs of entities. With the need to model interactions among more than two entities, significant research has focused on higher-order networks and ways to represent, analyze, and learn from them. There are two main directions to studying higher-order networks. One direction has focused on capturing higher-order patterns in traditional (dyadic) graphs by changing the basic unit of study from nodes to small frequently observed subgraphs, called motifs. As most existing network data comes in the form of pairwise dyadic relationships, studying higher-order structures within such graphs may uncover new insights. The second direction aims to directly model higher-order interactions using new and more complex representations such as simplicial complexes or hypergraphs. Some of these models have long been proposed, but improvements in computational power and the advent of new computational techniques have increased their popularity. Our goal in this paper is to provide a succinct yet comprehensive summary of the advanced higher-order network analysis techniques. We provide a systematic review of the foundations and algorithms, along with use cases and applications of higher-order networks in various scientific domains.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Network data has become widespread, larger, and more complex over the years. Traditional network data is dyadic, capturing the relations among pairs of entities. With the need to model interactions among more than two entities, significant research has focused on higher-order networks and ways to represent, analyze, and learn from them. There are two main directions to studying higher-order networks. One direction has focused on capturing higher-order patterns in traditional (dyadic) graphs by changing the basic unit of study from nodes to small frequently observed subgraphs, called motifs. As most existing network data comes in the form of pairwise dyadic relationships, studying higher-order structures within such graphs may uncover new insights. The second direction aims to directly model higher-order interactions using new and more complex representations such as simplicial complexes or hypergraphs. Some of these models have long been proposed, but improvements in computational power and the advent of new computational techniques have increased their popularity. Our goal in this paper is to provide a succinct yet comprehensive summary of the advanced higher-order network analysis techniques. We provide a systematic review of the foundations and algorithms, along with use cases and applications of higher-order networks in various scientific domains.
Nanabala, Chiradeep; Mohan, Chilukuri K.; Zafarani, Reza
Unmasking AI-Generated Fake News Across Multiple Domains Journal Article
In: Preprints, 2024.
@article{202405.0686,
title = {Unmasking AI-Generated Fake News Across Multiple Domains},
author = {Chiradeep Nanabala and Chilukuri K. Mohan and Reza Zafarani},
url = {https://doi.org/10.20944/preprints202405.0686.v1},
doi = {10.20944/preprints202405.0686.v1},
year = {2024},
date = {2024-05-01},
journal = {Preprints},
publisher = {Preprints},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abdolazimi, Reyhaneh; Jin, Shengmin; Varshney, Pramod K.; Zafarani, Reza
Harnessing the Power of Noise: A Survey of Techniques and Applications Miscellaneous
2024.
@misc{abdolazimi2024harnessingpowernoisesurvey,
title = {Harnessing the Power of Noise: A Survey of Techniques and Applications},
author = {Reyhaneh Abdolazimi and Shengmin Jin and Pramod K. Varshney and Reza Zafarani},
url = {https://arxiv.org/abs/2410.06348},
year = {2024},
date = {2024-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
2023
Li, Jiayu; Zhang, Tianyun; Jin, Shengmin; Zafarani, Reza
Semi-Supervised Graph Ultra-Sparsifier Using Reweighted $ell_1$ Optimization Proceedings Article
In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5, IEEE 2023.
@inproceedings{li2023semi,
title = {Semi-Supervised Graph Ultra-Sparsifier Using Reweighted $ell_1$ Optimization},
author = {Jiayu Li and Tianyun Zhang and Shengmin Jin and Reza Zafarani},
year = {2023},
date = {2023-01-01},
booktitle = {ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {1–5},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhou, Xinyi; Li, Jiayu; Li, Qinzhou; Zafarani, Reza
Linguistic-style-aware Neural Networks for Fake News Detection Miscellaneous
2023.
@misc{zhou2023linguisticstyleawareneuralnetworksfake,
title = {Linguistic-style-aware Neural Networks for Fake News Detection},
author = {Xinyi Zhou and Jiayu Li and Qinzhou Li and Reza Zafarani},
url = {https://arxiv.org/abs/2301.02792},
year = {2023},
date = {2023-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Abdolazimi, Reyhaneh; Zafarani, Reza
The Advantages of Adding Noise Proceedings Article
In: Proceedings of the International World Wide Web Conference 2023 (TheWebConf 2023), 2023.
@inproceedings{abdolazimi2023WWW,
title = {The Advantages of Adding Noise},
author = {Reyhaneh Abdolazimi and Reza Zafarani},
year = {2023},
date = {2023-01-01},
booktitle = {Proceedings of the International World Wide Web Conference 2023 (TheWebConf 2023)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2022
Tian, Hao; Jin, Shengmin; Zafarani, Reza
Exploiting Cross-Order Patterns and Link Prediction in Higher-Order Networks Proceedings Article
In: 2022 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1-9, IEEE Computer Society, Los Alamitos, CA, USA, 2022.
@inproceedings{10031242,
title = {Exploiting Cross-Order Patterns and Link Prediction in Higher-Order Networks},
author = {Hao Tian and Shengmin Jin and Reza Zafarani},
url = {https://doi.ieeecomputersociety.org/10.1109/ICDMW58026.2022.00156},
doi = {10.1109/ICDMW58026.2022.00156},
year = {2022},
date = {2022-12-01},
booktitle = {2022 IEEE International Conference on Data Mining Workshops (ICDMW)},
pages = {1-9},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {With the demand to model the relationships among three or more entities, higher-order networks are now more widespread across various domains. Relationships such as multiauthor collaborations, co-appearance of keywords, and copurchases can be naturally modeled as higher-order networks. However, due to (1) computational complexity and (2) insufficient higher-order data, exploring higher-order networks is often limited to order-3 motifs (or triangles). To address these problems, we explore and quantify similarites among various network orders. Our goal is to build relationships between different network orders and to solve higher-order problems using lower-order information. Similarities between different orders are not comparable directly. Hence, we introduce a set of general cross-order similarities, and a measure: subedge rate. Our experiments on multiple real-world datasets demonstrate that most higher-order networks have considerable consistency as we move from higher-orders to lower-orders. Utilizing this discovery, we develop a new cross-order framework for higher-order link prediction method. These methods can predict higher-order links from lower-order edges, which cannot be attained by current higher-order methods that rely on data from a single order.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
With the demand to model the relationships among three or more entities, higher-order networks are now more widespread across various domains. Relationships such as multiauthor collaborations, co-appearance of keywords, and copurchases can be naturally modeled as higher-order networks. However, due to (1) computational complexity and (2) insufficient higher-order data, exploring higher-order networks is often limited to order-3 motifs (or triangles). To address these problems, we explore and quantify similarites among various network orders. Our goal is to build relationships between different network orders and to solve higher-order problems using lower-order information. Similarities between different orders are not comparable directly. Hence, we introduce a set of general cross-order similarities, and a measure: subedge rate. Our experiments on multiple real-world datasets demonstrate that most higher-order networks have considerable consistency as we move from higher-orders to lower-orders. Utilizing this discovery, we develop a new cross-order framework for higher-order link prediction method. These methods can predict higher-order links from lower-order edges, which cannot be attained by current higher-order methods that rely on data from a single order.
Jin, Shengmin; Tian, Hao; Li, Jiayu; Zafarani, Reza
A Spectral Representation of Networks: The Path of Subgraphs Proceedings Article
In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 698–708, Association for Computing Machinery, Washington DC, USA, 2022, ISBN: 9781450393850.
@inproceedings{10.1145/3534678.3539433,
title = {A Spectral Representation of Networks: The Path of Subgraphs},
author = {Shengmin Jin and Hao Tian and Jiayu Li and Reza Zafarani},
url = {https://doi.org/10.1145/3534678.3539433},
doi = {10.1145/3534678.3539433},
isbn = {9781450393850},
year = {2022},
date = {2022-01-01},
booktitle = {Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages = {698–708},
publisher = {Association for Computing Machinery},
address = {Washington DC, USA},
series = {KDD '22},
abstract = {Network representation learning has played a critical role in studying networks. One way to study a graph is to focus on its spectrum, i.e., the eigenvalue distribution of its associated matrices. Recent advancements in spectral graph theory show that spectral moments of a network can be used to capture the network structure and various graph properties. However, sometimes networks with different structures or sizes can have the same or similar spectral moments, not to mention the existence of the cospectral graphs. To address such problems, we propose a 3D network representation that relies on the spectral information of subgraphs: the Spectral Path, a path connecting the spectral moments of the network and those of its subgraphs of different sizes. We show that the spectral path is interpretable and can capture relationship between a network and its subgraphs, for which we present a theoretical foundation. We demonstrate the effectiveness of the spectral path in applications such as network visualization and network identification.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Network representation learning has played a critical role in studying networks. One way to study a graph is to focus on its spectrum, i.e., the eigenvalue distribution of its associated matrices. Recent advancements in spectral graph theory show that spectral moments of a network can be used to capture the network structure and various graph properties. However, sometimes networks with different structures or sizes can have the same or similar spectral moments, not to mention the existence of the cospectral graphs. To address such problems, we propose a 3D network representation that relies on the spectral information of subgraphs: the Spectral Path, a path connecting the spectral moments of the network and those of its subgraphs of different sizes. We show that the spectral path is interpretable and can capture relationship between a network and its subgraphs, for which we present a theoretical foundation. We demonstrate the effectiveness of the spectral path in applications such as network visualization and network identification.
Jin, Shengmin; Ma, Rui; Li, Jiayu; Eftekharnejad, Sara; Zafarani, Reza
A Spectral Measure for Network Robustness: Assessment, Design, and Evolution Proceedings Article
In: 2022 IEEE International Conference on Knowledge Graph (ICKG), pp. 97-104, 2022.
@inproceedings{10029997,
title = {A Spectral Measure for Network Robustness: Assessment, Design, and Evolution},
author = {Shengmin Jin and Rui Ma and Jiayu Li and Sara Eftekharnejad and Reza Zafarani},
doi = {10.1109/ICKG55886.2022.00020},
year = {2022},
date = {2022-01-01},
booktitle = {2022 IEEE International Conference on Knowledge Graph (ICKG)},
pages = {97-104},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jin, Shengmin; Phoha, Vir V.; Zafarani, Reza
Graph-Based Identification and Authentication: A Stochastic Kronecker Approach Journal Article
In: IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 7, pp. 3282-3294, 2022.
@article{9204439,
title = {Graph-Based Identification and Authentication: A Stochastic Kronecker Approach},
author = {Shengmin Jin and Vir V. Phoha and Reza Zafarani},
doi = {10.1109/TKDE.2020.3025989},
year = {2022},
date = {2022-01-01},
journal = {IEEE Transactions on Knowledge and Data Engineering},
volume = {34},
number = {7},
pages = {3282-3294},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Li, Jiayu; Zhang, Tianyun; Jin, Shengmin; Fardad, Makan; Zafarani, Reza
AdverSparse: An Adversarial Attack Framework for Deep Spatial-Temporal Graph Neural Networks Proceedings Article
In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5857-5861, 2022.
@inproceedings{9747850,
title = {AdverSparse: An Adversarial Attack Framework for Deep Spatial-Temporal Graph Neural Networks},
author = {Jiayu Li and Tianyun Zhang and Shengmin Jin and Makan Fardad and Reza Zafarani},
doi = {10.1109/ICASSP43922.2022.9747850},
year = {2022},
date = {2022-01-01},
booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {5857-5861},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhou, Xinyi; Shu, Kai; Phoha, Vir V.; Liu, Huan; Zafarani, Reza
“This is Fake! Shared It by Mistake”:Assessing the Intent of Fake News Spreaders Proceedings Article
In: Proceedings of the ACM Web Conference 2022, pp. 3685–3694, Association for Computing Machinery, Virtual Event, Lyon, France, 2022, ISBN: 9781450390965.
@inproceedings{10.1145/3485447.3512264,
title = {“This is Fake! Shared It by Mistake”:Assessing the Intent of Fake News Spreaders},
author = {Xinyi Zhou and Kai Shu and Vir V. Phoha and Huan Liu and Reza Zafarani},
url = {https://doi.org/10.1145/3485447.3512264},
doi = {10.1145/3485447.3512264},
isbn = {9781450390965},
year = {2022},
date = {2022-01-01},
booktitle = {Proceedings of the ACM Web Conference 2022},
pages = {3685–3694},
publisher = {Association for Computing Machinery},
address = {Virtual Event, Lyon, France},
series = {WWW '22},
abstract = {Individuals can be misled by fake news and spread it unintentionally without knowing it is false. This phenomenon has been frequently observed but has not been investigated. Our aim in this work is to assess the intent of fake news spreaders. To distinguish between intentional versus unintentional spreading, we study the psychological explanations of unintentional spreading. With this foundation, we then propose an influence graph, using which we assess the intent of fake news spreaders. Our extensive experiments show that the assessed intent can help significantly differentiate between intentional and unintentional fake news spreaders. Furthermore, the estimated intent can significantly improve the current techniques that detect fake news. To our best knowledge, this is the first work to model individuals’ intent in fake news spreading.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Individuals can be misled by fake news and spread it unintentionally without knowing it is false. This phenomenon has been frequently observed but has not been investigated. Our aim in this work is to assess the intent of fake news spreaders. To distinguish between intentional versus unintentional spreading, we study the psychological explanations of unintentional spreading. With this foundation, we then propose an influence graph, using which we assess the intent of fake news spreaders. Our extensive experiments show that the assessed intent can help significantly differentiate between intentional and unintentional fake news spreaders. Furthermore, the estimated intent can significantly improve the current techniques that detect fake news. To our best knowledge, this is the first work to model individuals’ intent in fake news spreading.
Abdolazimi, Reyhaneh; Zafarani, Reza
Noise Enhancement: Techniques and Applications Proceedings Article
In: Proceedings of the SIAM International Conference on Data Mining (SDM22), 2022.
@inproceedings{abdolazimi2022SDM,
title = {Noise Enhancement: Techniques and Applications},
author = {Reyhaneh Abdolazimi and Reza Zafarani},
year = {2022},
date = {2022-01-01},
booktitle = {Proceedings of the SIAM International Conference on Data Mining (SDM22)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jin, Shengmin; Koutra, Danai; Zafarani, Reza
Interpretable Network Representations Proceedings Article
In: Proceedings of the Web Conference (TheWebConference 22), 2022.
@inproceedings{jin2022WWW,
title = {Interpretable Network Representations},
author = {Shengmin Jin and Danai Koutra and Reza Zafarani},
year = {2022},
date = {2022-01-01},
booktitle = {Proceedings of the Web Conference (TheWebConference 22)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2021
Yang, Chen; Zhou, Xinyi; Zafarani, Reza
CHECKED: Chinese COVID-19 fake news dataset Journal Article
In: Social Network Analysis and Minining (SNAM), vol. 11, no. 1, pp. 58:1-8, 2021.
@article{Yang2021-gf,
title = {CHECKED: Chinese COVID-19 fake news dataset},
author = {Chen Yang and Xinyi Zhou and Reza Zafarani},
year = {2021},
date = {2021-06-01},
journal = {Social Network Analysis and Minining (SNAM)},
volume = {11},
number = {1},
pages = {58:1-8},
address = {Germany},
abstract = {COVID-19 has impacted all lives. To maintain social distancing
and avoiding exposure, works and lives have gradually moved
online. Under this trend, social media usage to obtain COVID-19
news has increased. Also, misinformation on COVID-19 is
frequently spread on social media. In this work, we develop
CHECKED, the first Chinese dataset on COVID-19 misinformation.
CHECKED provides a total 2,104 verified microblogs related to
COVID-19 from December 2019 to August 2020, identified by using a
specific list of keywords. Correspondingly, CHECKED includes
1,868,175 reposts, 1,185,702 comments, and 56,852,736 likes that
reveal how these verified microblogs are spread and reacted on
Weibo. The dataset contains a rich set of multimedia information
for each microblog including ground-truth label, textual, visual,
temporal, and network information. Extensive experiments have
been conducted to analyze CHECKED data and to provide benchmark
results for well-established methods when predicting fake news
using CHECKED. We hope that CHECKED can facilitate studies that
target misinformation on coronavirus. The dataset is available at
https://github.com/cyang03/CHECKED.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
COVID-19 has impacted all lives. To maintain social distancing
and avoiding exposure, works and lives have gradually moved
online. Under this trend, social media usage to obtain COVID-19
news has increased. Also, misinformation on COVID-19 is
frequently spread on social media. In this work, we develop
CHECKED, the first Chinese dataset on COVID-19 misinformation.
CHECKED provides a total 2,104 verified microblogs related to
COVID-19 from December 2019 to August 2020, identified by using a
specific list of keywords. Correspondingly, CHECKED includes
1,868,175 reposts, 1,185,702 comments, and 56,852,736 likes that
reveal how these verified microblogs are spread and reacted on
Weibo. The dataset contains a rich set of multimedia information
for each microblog including ground-truth label, textual, visual,
temporal, and network information. Extensive experiments have
been conducted to analyze CHECKED data and to provide benchmark
results for well-established methods when predicting fake news
using CHECKED. We hope that CHECKED can facilitate studies that
target misinformation on coronavirus. The dataset is available at
https://github.com/cyang03/CHECKED.
and avoiding exposure, works and lives have gradually moved
online. Under this trend, social media usage to obtain COVID-19
news has increased. Also, misinformation on COVID-19 is
frequently spread on social media. In this work, we develop
CHECKED, the first Chinese dataset on COVID-19 misinformation.
CHECKED provides a total 2,104 verified microblogs related to
COVID-19 from December 2019 to August 2020, identified by using a
specific list of keywords. Correspondingly, CHECKED includes
1,868,175 reposts, 1,185,702 comments, and 56,852,736 likes that
reveal how these verified microblogs are spread and reacted on
Weibo. The dataset contains a rich set of multimedia information
for each microblog including ground-truth label, textual, visual,
temporal, and network information. Extensive experiments have
been conducted to analyze CHECKED data and to provide benchmark
results for well-established methods when predicting fake news
using CHECKED. We hope that CHECKED can facilitate studies that
target misinformation on coronavirus. The dataset is available at
https://github.com/cyang03/CHECKED.
Li, Jiayu; Zhang, Tianyun; Tian, Hao; Jin, Shengmin; Fardad, Makan; Zafarani, Reza
Graph Sparsification with Graph Convolutional Networks Journal Article
In: International Journal of Data Science and Analytics (JDSA), 2021.
@article{li2021SGCNJournal,
title = {Graph Sparsification with Graph Convolutional Networks},
author = {Jiayu Li and Tianyun Zhang and Hao Tian and Shengmin Jin and Makan Fardad and Reza Zafarani},
year = {2021},
date = {2021-01-01},
journal = {International Journal of Data Science and Analytics (JDSA)},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Abdolazimi, Reyhaneh; Zafarani, Reza
Noise-Enhanced Unsupervised Link Prediction Proceedings Article
In: Karlapalem, Kamal; Cheng, Hong; Ramakrishnan, Naren; Agrawal, R. K.; Reddy, P. Krishna; Srivastava, Jaideep; Chakraborty, Tanmoy (Ed.): Advances in Knowledge Discovery and Data Mining, pp. 472–487, Springer International Publishing, Cham, 2021, ISBN: 978-3-030-75762-5.
@inproceedings{10.1007/978-3-030-75762-5_38,
title = {Noise-Enhanced Unsupervised Link Prediction},
author = {Reyhaneh Abdolazimi and Reza Zafarani},
editor = {Kamal Karlapalem and Hong Cheng and Naren Ramakrishnan and R. K. Agrawal and P. Krishna Reddy and Jaideep Srivastava and Tanmoy Chakraborty},
isbn = {978-3-030-75762-5},
year = {2021},
date = {2021-01-01},
booktitle = {Advances in Knowledge Discovery and Data Mining},
pages = {472–487},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Link prediction has attracted attention from multiple research areas. Although several – mostly unsupervised – link prediction methods have been proposed, improving them is still under study. In several fields of science, noise is used as an advantage to improve information processing, inspiring us to also investigate noise enhancement in link prediction. In this research, we study link prediction from a data preprocessing point of view by introducing a noise-enhanced link prediction framework that improves the links predicted by current link prediction heuristics. The framework proposes three noise methods to help predict better links. Theoretical explanation and extensive experiments on synthetic and real-world datasets show that our framework helps improve current link prediction methods.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Link prediction has attracted attention from multiple research areas. Although several – mostly unsupervised – link prediction methods have been proposed, improving them is still under study. In several fields of science, noise is used as an advantage to improve information processing, inspiring us to also investigate noise enhancement in link prediction. In this research, we study link prediction from a data preprocessing point of view by introducing a noise-enhanced link prediction framework that improves the links predicted by current link prediction heuristics. The framework proposes three noise methods to help predict better links. Theoretical explanation and extensive experiments on synthetic and real-world datasets show that our framework helps improve current link prediction methods.
2020
Zhou, Xinyi; Zafarani, Reza
A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities Journal Article
In: ACM Computing Surveys (CSUR), vol. 53, no. 5, 2020, ISSN: 0360-0300.
@article{zhou2020survey,
title = {A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities},
author = {Xinyi Zhou and Reza Zafarani},
url = {https://doi.org/10.1145/3395046},
doi = {10.1145/3395046},
issn = {0360-0300},
year = {2020},
date = {2020-09-01},
journal = {ACM Computing Surveys (CSUR)},
volume = {53},
number = {5},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {The explosive growth in fake news and its erosion to democracy, justice, and public trust has increased the demand for fake news detection and intervention. This survey reviews and evaluates methods that can detect fake news from four perspectives: the false knowledge it carries, its writing style, its propagation patterns, and the credibility of its source. The survey also highlights some potential research tasks based on the review. In particular, we identify and detail related fundamental theories across various disciplines to encourage interdisciplinary research on fake news. It is our hope that this survey can facilitate collaborative efforts among experts in computer and information sciences, social sciences, political science, and journalism to research fake news, where such efforts can lead to fake news detection that is not only efficient but, more importantly, explainable.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The explosive growth in fake news and its erosion to democracy, justice, and public trust has increased the demand for fake news detection and intervention. This survey reviews and evaluates methods that can detect fake news from four perspectives: the false knowledge it carries, its writing style, its propagation patterns, and the credibility of its source. The survey also highlights some potential research tasks based on the review. In particular, we identify and detail related fundamental theories across various disciplines to encourage interdisciplinary research on fake news. It is our hope that this survey can facilitate collaborative efforts among experts in computer and information sciences, social sciences, political science, and journalism to research fake news, where such efforts can lead to fake news detection that is not only efficient but, more importantly, explainable.
Zhou, Xinyi; Jain, Atishay; Phoha, Vir V.; Zafarani, Reza
Fake News Early Detection: A Theory-Driven Model Journal Article
In: Digital Threats: Research and Practice, vol. 1, no. 2, 2020, ISSN: 2692-1626, (newline $~$hfill faTrophy$~$ Selected for highlighting in ACM’s AI/ML showcase on the Kudos platform.).
@article{zhou2020fake,
title = {Fake News Early Detection: A Theory-Driven Model},
author = {Xinyi Zhou and Atishay Jain and Vir V. Phoha and Reza Zafarani},
url = {https://doi.org/10.1145/3377478},
doi = {10.1145/3377478},
issn = {2692-1626},
year = {2020},
date = {2020-06-01},
journal = {Digital Threats: Research and Practice},
volume = {1},
number = {2},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Massive dissemination of fake news and its potential to erode democracy has increased the demand for accurate fake news detection. Recent advancements in this area have proposed novel techniques that aim to detect fake news by exploring how it propagates on social networks. Nevertheless, to detect fake news at an early stage, i.e., when it is published on a news outlet but not yet spread on social media, one cannot rely on news propagation information as it does not exist. Hence, there is a strong need to develop approaches that can detect fake news by focusing on news content. In this article, a theory-driven model is proposed for fake news detection. The method investigates news content at various levels: lexicon-level, syntax-level, semantic-level, and discourse-level. We represent news at each level, relying on well-established theories in social and forensic psychology. Fake news detection is then conducted within a supervised machine learning framework. As an interdisciplinary research, our work explores potential fake news patterns, enhances the interpretability in fake news feature engineering, and studies the relationships among fake news, deception/disinformation, and clickbaits. Experiments conducted on two real-world datasets indicate the proposed method can outperform the state-of-the-art and enable fake news early detection when there is limited content information.},
note = {newline $~$hfill faTrophy$~$ Selected for highlighting in ACM’s AI/ML showcase on the Kudos platform.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Massive dissemination of fake news and its potential to erode democracy has increased the demand for accurate fake news detection. Recent advancements in this area have proposed novel techniques that aim to detect fake news by exploring how it propagates on social networks. Nevertheless, to detect fake news at an early stage, i.e., when it is published on a news outlet but not yet spread on social media, one cannot rely on news propagation information as it does not exist. Hence, there is a strong need to develop approaches that can detect fake news by focusing on news content. In this article, a theory-driven model is proposed for fake news detection. The method investigates news content at various levels: lexicon-level, syntax-level, semantic-level, and discourse-level. We represent news at each level, relying on well-established theories in social and forensic psychology. Fake news detection is then conducted within a supervised machine learning framework. As an interdisciplinary research, our work explores potential fake news patterns, enhances the interpretability in fake news feature engineering, and studies the relationships among fake news, deception/disinformation, and clickbaits. Experiments conducted on two real-world datasets indicate the proposed method can outperform the state-of-the-art and enable fake news early detection when there is limited content information.
Sitaula, Niraj; Mohan, Chilukuri K.; Grygiel, Jennifer; Zhou, Xinyi; Zafarani, Reza
Credibility-Based Fake News Detection Book Chapter
In: Shu, Kai; Wang, Suhang; Lee, Dongwon; Liu, Huan (Ed.): Disinformation, Misinformation, and Fake News in Social Media: Emerging Research Challenges and Opportunities, pp. 163–182, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-42699-6.
@inbook{sitaula2020credibility,
title = {Credibility-Based Fake News Detection},
author = {Niraj Sitaula and Chilukuri K. Mohan and Jennifer Grygiel and Xinyi Zhou and Reza Zafarani},
editor = {Kai Shu and Suhang Wang and Dongwon Lee and Huan Liu},
url = {https://doi.org/10.1007/978-3-030-42699-6_9},
doi = {10.1007/978-3-030-42699-6_9},
isbn = {978-3-030-42699-6},
year = {2020},
date = {2020-01-01},
booktitle = {Disinformation, Misinformation, and Fake News in Social Media: Emerging Research Challenges and Opportunities},
pages = {163–182},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Fake news can significantly misinform people who often rely on online sources and social media for their information. Current research on fake news detection has mostly focused on analyzing fake news content and how it propagates on a network of users. In this paper, we emphasize the detection of fake news by assessing its credibility. By analyzing public fake news data, we show that information on news sources (and authors) can be a strong indicator of credibility. Our findings suggest that an author's history of association with fake news, and the number of authors of a news article, can play a significant role in detecting fake news. Our approach can help improve traditional fake news detection methods, wherein content features are often used to detect fake news.},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Fake news can significantly misinform people who often rely on online sources and social media for their information. Current research on fake news detection has mostly focused on analyzing fake news content and how it propagates on a network of users. In this paper, we emphasize the detection of fake news by assessing its credibility. By analyzing public fake news data, we show that information on news sources (and authors) can be a strong indicator of credibility. Our findings suggest that an author's history of association with fake news, and the number of authors of a news article, can play a significant role in detecting fake news. Our approach can help improve traditional fake news detection methods, wherein content features are often used to detect fake news.
Ma, Rui; Jin, Shengmin; Eftekharnejad, Sara; Zafarani, Reza; Philippe, Wolf Peter Jean
A Probabilistic Cascading Failure Model for Dynamic Operating Conditions Journal Article
In: IEEE Access, vol. 8, pp. 61741-61753, 2020.
@article{ma2020probabilistic,
title = {A Probabilistic Cascading Failure Model for Dynamic Operating Conditions},
author = {Rui Ma and Shengmin Jin and Sara Eftekharnejad and Reza Zafarani and Wolf Peter Jean Philippe},
doi = {10.1109/ACCESS.2020.2984240},
year = {2020},
date = {2020-01-01},
journal = {IEEE Access},
volume = {8},
pages = {61741-61753},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhou, Xinyi; Mulay, Apurva; Ferrara, Emilio; Zafarani, Reza
ReCOVery: A Multimodal Repository for COVID-19 News Credibility Research Proceedings Article
In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 3205–3212, Association for Computing Machinery, Virtual Event, Ireland, 2020, ISBN: 9781450368599.
@inproceedings{10.1145/3340531.3412880,
title = {ReCOVery: A Multimodal Repository for COVID-19 News Credibility Research},
author = {Xinyi Zhou and Apurva Mulay and Emilio Ferrara and Reza Zafarani},
url = {https://doi.org/10.1145/3340531.3412880},
doi = {10.1145/3340531.3412880},
isbn = {9781450368599},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 29th ACM International Conference on Information & Knowledge Management},
pages = {3205–3212},
publisher = {Association for Computing Machinery},
address = {Virtual Event, Ireland},
series = {CIKM '20},
abstract = {First identified in Wuhan, China, in December 2019, the outbreak of COVID-19 has been declared as a global emergency in January, and a pandemic in March 2020 by the World Health Organization (WHO). Along with this pandemic, we are also experiencing an "infodemic" of information with low credibility such as fake news and conspiracies. In this work, we present ReCOVery, a repository designed and constructed to facilitate research on combating such information regarding COVID-19. We first broadly search and investigate ~2,000 news publishers, from which 60 are identified with extreme [high or low] levels of credibility. By inheriting the credibility of the media on which they were published, a total of 2,029 news articles on coronavirus, published from January to May 2020, are collected in the repository, along with 140,820 tweets that reveal how these news articles have spread on the Twitter social network. The repository provides multimodal information of news articles on coronavirus, including textual, visual, temporal, and network information. The way that news credibility is obtained allows a trade-off between dataset scalability and label accuracy. Extensive experiments are conducted to present data statistics and distributions, as well as to provide baseline performances for predicting news credibility so that future methods can be compared. Our repository is available at http://coronavirus-fakenews.com.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
First identified in Wuhan, China, in December 2019, the outbreak of COVID-19 has been declared as a global emergency in January, and a pandemic in March 2020 by the World Health Organization (WHO). Along with this pandemic, we are also experiencing an "infodemic" of information with low credibility such as fake news and conspiracies. In this work, we present ReCOVery, a repository designed and constructed to facilitate research on combating such information regarding COVID-19. We first broadly search and investigate ~2,000 news publishers, from which 60 are identified with extreme [high or low] levels of credibility. By inheriting the credibility of the media on which they were published, a total of 2,029 news articles on coronavirus, published from January to May 2020, are collected in the repository, along with 140,820 tweets that reveal how these news articles have spread on the Twitter social network. The repository provides multimodal information of news articles on coronavirus, including textual, visual, temporal, and network information. The way that news credibility is obtained allows a trade-off between dataset scalability and label accuracy. Extensive experiments are conducted to present data statistics and distributions, as well as to provide baseline performances for predicting news credibility so that future methods can be compared. Our repository is available at http://coronavirus-fakenews.com.
Li, Jiayu; Zhang, Tianyun; Tian, Hao; Jin, Shengmin; Fardad, Makan; Zafarani, Reza
SGCN: A Graph Sparsifier Based on Graph Convolutional Networks Proceedings Article
In: Lauw, Hady W.; Wong, Raymond Chi-Wing; Ntoulas, Alexandros; Lim, Ee-Peng; Ng, See-Kiong; Pan, Sinno Jialin (Ed.): Advances in Knowledge Discovery and Data Mining, pp. 275–287, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-47426-3.
@inproceedings{10.1007/978-3-030-47426-3_22,
title = {SGCN: A Graph Sparsifier Based on Graph Convolutional Networks},
author = {Jiayu Li and Tianyun Zhang and Hao Tian and Shengmin Jin and Makan Fardad and Reza Zafarani},
editor = {Hady W. Lauw and Raymond Chi-Wing Wong and Alexandros Ntoulas and Ee-Peng Lim and See-Kiong Ng and Sinno Jialin Pan},
isbn = {978-3-030-47426-3},
year = {2020},
date = {2020-01-01},
booktitle = {Advances in Knowledge Discovery and Data Mining},
pages = {275–287},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Graphs are ubiquitous across the globe and within science and engineering. With graphs growing in size, node classification on large graphs can be space and time consuming, even with powerful classifiers such as Graph Convolutional Networks (GCNs). Hence, some questions are raised, particularly, whether one can keep only some of the edges of a graph while maintaining prediction performance for node classification, or train classifiers on specific subgraphs instead of a whole graph with limited performance loss in node classification. To address these questions, we propose Sparsified Graph Convolutional Network (SGCN), a neural network graph sparsifier that sparsifies a graph by pruning some edges. We formulate sparsification as an optimization problem, which we solve by an Alternating Direction Method of Multipliers (ADMM)-based solution. We show that sparsified graphs provided by SGCN can be used as inputs to GCN, leading to better or comparable node classification performance with that of original graphs in GCN, DeepWalk, and GraphSAGE.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Graphs are ubiquitous across the globe and within science and engineering. With graphs growing in size, node classification on large graphs can be space and time consuming, even with powerful classifiers such as Graph Convolutional Networks (GCNs). Hence, some questions are raised, particularly, whether one can keep only some of the edges of a graph while maintaining prediction performance for node classification, or train classifiers on specific subgraphs instead of a whole graph with limited performance loss in node classification. To address these questions, we propose Sparsified Graph Convolutional Network (SGCN), a neural network graph sparsifier that sparsifies a graph by pruning some edges. We formulate sparsification as an optimization problem, which we solve by an Alternating Direction Method of Multipliers (ADMM)-based solution. We show that sparsified graphs provided by SGCN can be used as inputs to GCN, leading to better or comparable node classification performance with that of original graphs in GCN, DeepWalk, and GraphSAGE.
Zhou, Xinyi; Jin, Shengmin; Zafarani, Reza
Sentiment Paradoxes in Social Networks: Why Your Friends Are More Positive Than You? Journal Article
In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 14, no. 1, pp. 798-807, 2020.
@article{Zhou_Jin_Zafarani_2020,
title = {Sentiment Paradoxes in Social Networks: Why Your Friends Are More Positive Than You?},
author = {Xinyi Zhou and Shengmin Jin and Reza Zafarani},
url = {https://ojs.aaai.org/index.php/ICWSM/article/view/7344},
year = {2020},
date = {2020-01-01},
journal = {Proceedings of the International AAAI Conference on Web and Social Media},
volume = {14},
number = {1},
pages = {798-807},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zhou, Xinyi; Wu, Jindi; Zafarani, Reza
$mathsfSAFE$: Similarity-Aware Multi-modal Fake News Detection Proceedings Article
In: Lauw, Hady W.; Wong, Raymond Chi-Wing; Ntoulas, Alexandros; Lim, Ee-Peng; Ng, See-Kiong; Pan, Sinno Jialin (Ed.): Advances in Knowledge Discovery and Data Mining, pp. 354–367, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-47436-2.
@inproceedings{10.1007/978-3-030-47436-2_27,
title = {$mathsfSAFE$: Similarity-Aware Multi-modal Fake News Detection},
author = {Xinyi Zhou and Jindi Wu and Reza Zafarani},
editor = {Hady W. Lauw and Raymond Chi-Wing Wong and Alexandros Ntoulas and Ee-Peng Lim and See-Kiong Ng and Sinno Jialin Pan},
isbn = {978-3-030-47436-2},
year = {2020},
date = {2020-01-01},
booktitle = {Advances in Knowledge Discovery and Data Mining},
pages = {354–367},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Effective detection of fake news has recently attracted significant attention. Current studies have made significant contributions to predicting fake news with less focus on exploiting the relationship (similarity) between the textual and visual information in news articles. Attaching importance to such similarity helps identify fake news stories that, for example, attempt to use irrelevant images to attract readers' attention. In this work, we propose a $$backslashmathsf S$$imilarity-$$backslashmathsf A$$ware $$backslashmathsf F$$ak$$backslashmathsf E$$ news detection method ($$backslashmathsf SAFE$$) which investigates multi-modal (textual and visual) information of news articles. First, neural networks are adopted to separately extract textual and visual features for news representation. We further investigate the relationship between the extracted features across modalities. Such representations of news textual and visual information along with their relationship are jointly learned and used to predict fake news. The proposed method facilitates recognizing the falsity of news articles based on their text, images, or their ``mismatches.'' We conduct extensive experiments on large-scale real-world data, which demonstrate the effectiveness of the proposed method.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Effective detection of fake news has recently attracted significant attention. Current studies have made significant contributions to predicting fake news with less focus on exploiting the relationship (similarity) between the textual and visual information in news articles. Attaching importance to such similarity helps identify fake news stories that, for example, attempt to use irrelevant images to attract readers' attention. In this work, we propose a $$backslashmathsf S$$imilarity-$$backslashmathsf A$$ware $$backslashmathsf F$$ak$$backslashmathsf E$$ news detection method ($$backslashmathsf SAFE$$) which investigates multi-modal (textual and visual) information of news articles. First, neural networks are adopted to separately extract textual and visual features for news representation. We further investigate the relationship between the extracted features across modalities. Such representations of news textual and visual information along with their relationship are jointly learned and used to predict fake news. The proposed method facilitates recognizing the falsity of news articles based on their text, images, or their ``mismatches.'' We conduct extensive experiments on large-scale real-world data, which demonstrate the effectiveness of the proposed method.
Jin, Shengmin; Wituszynski, Richard; Caiello-Gingold, Max; Zafarani, Reza
WebShapes: Network Visualization with 3D Shapes Proceedings Article
In: Proceedings of the 13th International Conference on Web Search and Data Mining, pp. 837–840, Association for Computing Machinery, Houston, TX, USA, 2020, ISBN: 9781450368223.
@inproceedings{10.1145/3336191.3371867,
title = {WebShapes: Network Visualization with 3D Shapes},
author = {Shengmin Jin and Richard Wituszynski and Max Caiello-Gingold and Reza Zafarani},
url = {https://doi.org/10.1145/3336191.3371867},
doi = {10.1145/3336191.3371867},
isbn = {9781450368223},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 13th International Conference on Web Search and Data Mining},
pages = {837–840},
publisher = {Association for Computing Machinery},
address = {Houston, TX, USA},
series = {WSDM '20},
abstract = {Network visualization has played a critical role in graph analysis, as it not only presents a big picture of a network but also helps reveal the structural information of a network. The most popular visual representation of networks is the node-link diagram. However, visualizing a large network with the node-link diagram can be challenging due to the difficulty in obtaining an optimal graph layout. To address this challenge, a recent advancement in network representation: network shape, allows one to compactly represent a network and its subgraphs with the distribution of their embeddings. Inspired by this research, we have designed a web platform WebShapes that enables researchers and practitioners to visualize their network data as customized 3D shapes (http://b.link/webshapes). Furthermore, we provide a case study on real-world networks to explore the sensitivity of network shapes to different graph sampling, embedding, and fitting methods, and we show examples of understanding networks through their network shapes.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Network visualization has played a critical role in graph analysis, as it not only presents a big picture of a network but also helps reveal the structural information of a network. The most popular visual representation of networks is the node-link diagram. However, visualizing a large network with the node-link diagram can be challenging due to the difficulty in obtaining an optimal graph layout. To address this challenge, a recent advancement in network representation: network shape, allows one to compactly represent a network and its subgraphs with the distribution of their embeddings. Inspired by this research, we have designed a web platform WebShapes that enables researchers and practitioners to visualize their network data as customized 3D shapes (http://b.link/webshapes). Furthermore, we provide a case study on real-world networks to explore the sensitivity of network shapes to different graph sampling, embedding, and fitting methods, and we show examples of understanding networks through their network shapes.
Jin, Shengmin; Zafarani, Reza
The Spectral Zoo of Networks: Embedding and Visualizing Networks with Spectral Moments Proceedings Article
In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1426–1434, Association for Computing Machinery, Virtual Event, CA, USA, 2020, ISBN: 9781450379984.
@inproceedings{10.1145/3394486.3403195,
title = {The Spectral Zoo of Networks: Embedding and Visualizing Networks with Spectral Moments},
author = {Shengmin Jin and Reza Zafarani},
url = {https://doi.org/10.1145/3394486.3403195},
doi = {10.1145/3394486.3403195},
isbn = {9781450379984},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
pages = {1426–1434},
publisher = {Association for Computing Machinery},
address = {Virtual Event, CA, USA},
series = {KDD '20},
abstract = {Network embedding methods have been widely and successfully used in network-based applications such as node classification and link prediction. However, an ideal network embedding should not only be useful for machine learning, but interpretable. We introduce a spectral embedding method for a network, its Spectral Point, which is basically the first few spectral moments of a network. Spectral moments are interpretable, where we prove their close relationships to network structure (e.g. number of triangles and squares) and various network properties (e.g. degree distribution, clustering coefficient, and network connectivity). Using spectral points, we introduce a visualizable and bounded 3D embedding space for all possible graphs, in which one can characterize various types of graphs (e.g., cycles), or real-world networks from different categories (e.g., social or biological networks). We demonstrate that spectral points can be used for network identification (i.e., what network is this subgraph sampled from?) and that by using just the first few moments one does not lose much predictive power.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Network embedding methods have been widely and successfully used in network-based applications such as node classification and link prediction. However, an ideal network embedding should not only be useful for machine learning, but interpretable. We introduce a spectral embedding method for a network, its Spectral Point, which is basically the first few spectral moments of a network. Spectral moments are interpretable, where we prove their close relationships to network structure (e.g. number of triangles and squares) and various network properties (e.g. degree distribution, clustering coefficient, and network connectivity). Using spectral points, we introduce a visualizable and bounded 3D embedding space for all possible graphs, in which one can characterize various types of graphs (e.g., cycles), or real-world networks from different categories (e.g., social or biological networks). We demonstrate that spectral points can be used for network identification (i.e., what network is this subgraph sampled from?) and that by using just the first few moments one does not lose much predictive power.
Abdolazimi, Reyhaneh; Jin, Shengmin; Zafarani, Reza
Noise-Enhanced Community Detection Proceedings Article
In: Proceedings of the 31st ACM Conference on Hypertext and Social Media, pp. 271–280, Association for Computing Machinery, Virtual Event, USA, 2020, ISBN: 9781450370981, (newline $~$hfill faTrophy Best Paper Candidate).
@inproceedings{10.1145/3372923.3404788,
title = {Noise-Enhanced Community Detection},
author = {Reyhaneh Abdolazimi and Shengmin Jin and Reza Zafarani},
url = {https://doi.org/10.1145/3372923.3404788},
doi = {10.1145/3372923.3404788},
isbn = {9781450370981},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 31st ACM Conference on Hypertext and Social Media},
pages = {271–280},
publisher = {Association for Computing Machinery},
address = {Virtual Event, USA},
series = {HT '20},
abstract = {Community structure plays a significant role in uncovering the structure of a network. While many community detection algorithms have been introduced, improving the quality of detected communities is still an open problem. In many areas of science, adding noise improves system performance and algorithm efficiency, motivating us to also explore the possibility of adding noise to improve community detection algorithms. We propose a noise-enhanced community detection framework that improves communities detected by existing community detection methods. The framework introduces three noise methods to help detect communities better. Theoretical justification and extensive experiments on synthetic and real-world datasets show that our framework helps community detection methods find better communities.},
note = {newline $~$hfill faTrophy Best Paper Candidate},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Community structure plays a significant role in uncovering the structure of a network. While many community detection algorithms have been introduced, improving the quality of detected communities is still an open problem. In many areas of science, adding noise improves system performance and algorithm efficiency, motivating us to also explore the possibility of adding noise to improve community detection algorithms. We propose a noise-enhanced community detection framework that improves communities detected by existing community detection methods. The framework introduces three noise methods to help detect communities better. Theoretical justification and extensive experiments on synthetic and real-world datasets show that our framework helps community detection methods find better communities.
Tian, Hao; Zafarani, Reza
Exploiting Common Neighbor Graph for Link Prediction Proceedings Article
In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 3333–3336, Association for Computing Machinery, Virtual Event, Ireland, 2020, ISBN: 9781450368599.
@inproceedings{10.1145/3340531.3417464,
title = {Exploiting Common Neighbor Graph for Link Prediction},
author = {Hao Tian and Reza Zafarani},
url = {https://doi.org/10.1145/3340531.3417464},
doi = {10.1145/3340531.3417464},
isbn = {9781450368599},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 29th ACM International Conference on Information & Knowledge Management},
pages = {3333–3336},
publisher = {Association for Computing Machinery},
address = {Virtual Event, Ireland},
series = {CIKM '20},
abstract = {Link prediction aims to predict whether two nodes in a network are likely to get connected. Motivated by its applications, e.g., in friend or product recommendation, link prediction has been extensively studied over the years. Most link prediction methods are designed based on specific assumptions that may or may not hold in different networks, leading to link prediction methods that are not generalizable. Here, we address this problem by proposing general link prediction methods that can capture network-specific patterns. Most link prediction methods rely on computing similarities between between nodes. By learning a γ-decaying model, the proposed methods can measure the pairwise similarities between nodes more accurately, even when only using common neighbor information, which is often used by current techniques.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Link prediction aims to predict whether two nodes in a network are likely to get connected. Motivated by its applications, e.g., in friend or product recommendation, link prediction has been extensively studied over the years. Most link prediction methods are designed based on specific assumptions that may or may not hold in different networks, leading to link prediction methods that are not generalizable. Here, we address this problem by proposing general link prediction methods that can capture network-specific patterns. Most link prediction methods rely on computing similarities between between nodes. By learning a γ-decaying model, the proposed methods can measure the pairwise similarities between nodes more accurately, even when only using common neighbor information, which is often used by current techniques.
2019
Zhou, Xinyi; Zafarani, Reza
Network-Based Fake News Detection: A Pattern-Driven Approach Journal Article
In: ACM SIGKDD Explorations Newsletter, vol. 21, no. 2, pp. 48–60, 2019, ISSN: 1931-0145.
@article{zhou2019network,
title = {Network-Based Fake News Detection: A Pattern-Driven Approach},
author = {Xinyi Zhou and Reza Zafarani},
url = {https://doi.org/10.1145/3373464.3373473},
doi = {10.1145/3373464.3373473},
issn = {1931-0145},
year = {2019},
date = {2019-11-01},
journal = {ACM SIGKDD Explorations Newsletter},
volume = {21},
number = {2},
pages = {48–60},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Fake news gains has gained significant momentum, strongly motivating the need for fake news research. Many fake news detection approaches have thus been proposed, where most of them heavily rely on news content. However, networkbased clues revealed when analyzing news propagation on social networks is an information that has hardly been comprehensively explored or used for fake news detection. We bridge this gap by proposing a network-based pattern-driven fake news detection approach. We aim to study the patterns of fake news in social networks, which refer to the news being spread, spreaders of the news and relationships among the spreaders. Empirical evidence and interpretations on the existence of such patterns are provided based on social psychological theories. These patterns are then represented at various network levels (i.e., node-level, ego-level, triad-level, community-level and the overall network) for being further utilized to detect fake news. The proposed approach enhances the explainability in fake news feature engineering. Experiments conducted on real-world data demonstrate that the proposed approach can outperform the state of the arts.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Fake news gains has gained significant momentum, strongly motivating the need for fake news research. Many fake news detection approaches have thus been proposed, where most of them heavily rely on news content. However, networkbased clues revealed when analyzing news propagation on social networks is an information that has hardly been comprehensively explored or used for fake news detection. We bridge this gap by proposing a network-based pattern-driven fake news detection approach. We aim to study the patterns of fake news in social networks, which refer to the news being spread, spreaders of the news and relationships among the spreaders. Empirical evidence and interpretations on the existence of such patterns are provided based on social psychological theories. These patterns are then represented at various network levels (i.e., node-level, ego-level, triad-level, community-level and the overall network) for being further utilized to detect fake news. The proposed approach enhances the explainability in fake news feature engineering. Experiments conducted on real-world data demonstrate that the proposed approach can outperform the state of the arts.
Shu, Kai; Zhou, Xinyi; Wang, Suhang; Zafarani, Reza; Liu, Huan
The Role of User Profiles for Fake News Detection Proceedings Article
In: Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 436–439, Association for Computing Machinery, Vancouver, British Columbia, Canada, 2019, ISBN: 9781450368681.
@inproceedings{10.1145/3341161.3342927,
title = {The Role of User Profiles for Fake News Detection},
author = {Kai Shu and Xinyi Zhou and Suhang Wang and Reza Zafarani and Huan Liu},
url = {https://doi.org/10.1145/3341161.3342927},
doi = {10.1145/3341161.3342927},
isbn = {9781450368681},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
pages = {436–439},
publisher = {Association for Computing Machinery},
address = {Vancouver, British Columbia, Canada},
series = {ASONAM '19},
abstract = {Consuming news from social media is becoming increasingly popular. Social media appeals to users due to its fast dissemination of information, low cost, and easy access. However, social media also enables the widespread of fake news. Due to the detrimental societal effects of fake news, detecting fake news has attracted increasing attention. However, the detection performance only using news contents is generally not satisfactory as fake news is written to mimic true news. Thus, there is a need for an in-depth understanding on the relationship between user profiles on social media and fake news. In this paper, we study the problem of understanding and exploiting user profiles on social media for fake news detection. In an attempt to understand connections between user profiles and fake news, first, we measure users' sharing behaviors and group representative users who are more likely to share fake and real news; then, we perform a comparative analysis of explicit and implicit profile features between these user groups, which reveals their potential to help differentiate fake news from real news. To exploit user profile features, we demonstrate the usefulness of these user profile features in a fake news classification task. We further validate the effectiveness of these features through feature importance analysis. The findings of this work lay the foundation for deeper exploration of user profile features of social media and enhance the capabilities for fake news detection.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Consuming news from social media is becoming increasingly popular. Social media appeals to users due to its fast dissemination of information, low cost, and easy access. However, social media also enables the widespread of fake news. Due to the detrimental societal effects of fake news, detecting fake news has attracted increasing attention. However, the detection performance only using news contents is generally not satisfactory as fake news is written to mimic true news. Thus, there is a need for an in-depth understanding on the relationship between user profiles on social media and fake news. In this paper, we study the problem of understanding and exploiting user profiles on social media for fake news detection. In an attempt to understand connections between user profiles and fake news, first, we measure users' sharing behaviors and group representative users who are more likely to share fake and real news; then, we perform a comparative analysis of explicit and implicit profile features between these user groups, which reveals their potential to help differentiate fake news from real news. To exploit user profile features, we demonstrate the usefulness of these user profile features in a fake news classification task. We further validate the effectiveness of these features through feature importance analysis. The findings of this work lay the foundation for deeper exploration of user profile features of social media and enhance the capabilities for fake news detection.
Hozhabrierdi, Pegah; Zafarani, Reza
The Impact of Graph Structure on Small-World Shortest Paths Proceedings Article
In: International Conference on Social Computing, Behavioral Modeling, and Prediction, Springer 2019.
@inproceedings{hozhabrierdiimpact,
title = {The Impact of Graph Structure on Small-World Shortest Paths},
author = {Pegah Hozhabrierdi and Reza Zafarani},
year = {2019},
date = {2019-01-01},
booktitle = {International Conference on Social Computing, Behavioral Modeling, and Prediction},
organization = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jin, Shengmin; Phoha, Vir; Zafarani, Reza
Network Identification and Authentication Proceedings Article
In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 1144-1149, 2019.
@inproceedings{jin2019network,
title = {Network Identification and Authentication},
author = {Shengmin Jin and Vir Phoha and Reza Zafarani},
doi = {10.1109/ICDM.2019.00138},
year = {2019},
date = {2019-01-01},
booktitle = {2019 IEEE International Conference on Data Mining (ICDM)},
pages = {1144-1149},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhou, Xinyi; Zafarani, Reza
Fake news detection: An interdisciplinary research Proceedings Article
In: Companion Proceedings of The 2019 World Wide Web Conference, pp. 1292–1292, 2019.
@inproceedings{zhou2019fake,
title = {Fake news detection: An interdisciplinary research},
author = {Xinyi Zhou and Reza Zafarani},
year = {2019},
date = {2019-01-01},
booktitle = {Companion Proceedings of The 2019 World Wide Web Conference},
pages = {1292–1292},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zhou, Xinyi; Zafarani, Reza; Shu, Kai; Liu, Huan
Fake news: Fundamental theories, detection strategies and challenges Proceedings Article
In: Proceedings of the twelfth ACM international conference on web search and data mining, pp. 836–837, 2019.
@inproceedings{zhou2019fakeWSDM,
title = {Fake news: Fundamental theories, detection strategies and challenges},
author = {Xinyi Zhou and Reza Zafarani and Kai Shu and Huan Liu},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the twelfth ACM international conference on web search and data mining},
pages = {836–837},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Zafarani, Reza; Zhou, Xinyi; Shu, Kai; Liu, Huan
Fake news research: Theories, detection strategies, and open problems Proceedings Article
In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3207–3208, 2019.
@inproceedings{zafarani2019fake,
title = {Fake news research: Theories, detection strategies, and open problems},
author = {Reza Zafarani and Xinyi Zhou and Kai Shu and Huan Liu},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
pages = {3207–3208},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
Jin, Shengmin; Zafarani, Reza
Representing Networks with 3D Shapes Proceedings Article
In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 177-186, 2018.
@inproceedings{jin2018representing,
title = {Representing Networks with 3D Shapes},
author = {Shengmin Jin and Reza Zafarani},
doi = {10.1109/ICDM.2018.00033},
year = {2018},
date = {2018-01-01},
booktitle = {2018 IEEE International Conference on Data Mining (ICDM)},
pages = {177-186},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jin, Shengmin; Zafarani, Reza
Sentiment Prediction in Social Networks Proceedings Article
In: 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1340-1347, 2018.
@inproceedings{8637419,
title = {Sentiment Prediction in Social Networks},
author = {Shengmin Jin and Reza Zafarani},
doi = {10.1109/ICDMW.2018.00190},
year = {2018},
date = {2018-01-01},
booktitle = {2018 IEEE International Conference on Data Mining Workshops (ICDMW)},
pages = {1340-1347},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2017
Shu, Kai; Wang, Suhang; Tang, Jiliang; Zafarani, Reza; Liu, Huan
User Identity Linkage across Online Social Networks: A Review Journal Article
In: ACM SIGKDD Explorations Newsletter, vol. 18, no. 2, pp. 5–17, 2017, ISSN: 1931-0145.
@article{shu2017user,
title = {User Identity Linkage across Online Social Networks: A Review},
author = {Kai Shu and Suhang Wang and Jiliang Tang and Reza Zafarani and Huan Liu},
url = {https://doi.org/10.1145/3068777.3068781},
doi = {10.1145/3068777.3068781},
issn = {1931-0145},
year = {2017},
date = {2017-03-01},
journal = {ACM SIGKDD Explorations Newsletter},
volume = {18},
number = {2},
pages = {5–17},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {The increasing popularity and diversity of social media sites has encouraged more and more people to participate on multiple online social networks to enjoy their services. Each user may create a user identity, which can includes profile, content, or network information, to represent his or her unique public figure in every social network. Thus, a fundamental question arises – can we link user identities across online social networks? User identity linkage across online social networks is an emerging task in social media and has attracted increasing attention in recent years. Advancements in user identity linkage could potentially impact various domains such as recommendation and link prediction. Due to the unique characteristics of social network data, this problem faces tremendous challenges. To tackle these challenges, recent approaches generally consist of (1) extracting features and (2) constructing predictive models from a variety of perspectives. In this paper, we review key achievements of user identity linkage across online social networks including stateof- the-art algorithms, evaluation metrics, and representative datasets. We also discuss related research areas, open problems, and future research directions for user identity linkage across online social networks.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The increasing popularity and diversity of social media sites has encouraged more and more people to participate on multiple online social networks to enjoy their services. Each user may create a user identity, which can includes profile, content, or network information, to represent his or her unique public figure in every social network. Thus, a fundamental question arises – can we link user identities across online social networks? User identity linkage across online social networks is an emerging task in social media and has attracted increasing attention in recent years. Advancements in user identity linkage could potentially impact various domains such as recommendation and link prediction. Due to the unique characteristics of social network data, this problem faces tremendous challenges. To tackle these challenges, recent approaches generally consist of (1) extracting features and (2) constructing predictive models from a variety of perspectives. In this paper, we review key achievements of user identity linkage across online social networks including stateof- the-art algorithms, evaluation metrics, and representative datasets. We also discuss related research areas, open problems, and future research directions for user identity linkage across online social networks.
Jin, Shengmin; Zafarani, Reza
Emotions in Social Networks: Distributions, Patterns, and Models Proceedings Article
In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 1907–1916, Association for Computing Machinery, Singapore, Singapore, 2017, ISBN: 9781450349185.
@inproceedings{jin2017emotions,
title = {Emotions in Social Networks: Distributions, Patterns, and Models},
author = {Shengmin Jin and Reza Zafarani},
url = {https://doi.org/10.1145/3132847.3132932},
doi = {10.1145/3132847.3132932},
isbn = {9781450349185},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings of the 2017 ACM on Conference on Information and Knowledge Management},
pages = {1907–1916},
publisher = {Association for Computing Machinery},
address = {Singapore, Singapore},
series = {CIKM '17},
abstract = {Understanding the role emotions play in social interactions has been a central research question in the social sciences. However, the challenge of obtaining large-scale data on human emotions has left the most fundamental questions on emotions less explored: How do emotions vary across individuals, evolve over time, and are connected to social ties?We address these questions using a large-scale dataset of users that contains both their emotions and social ties. Using this dataset, we identify patterns of human emotions on five different network levels, starting from the user-level and moving up to the whole-network level. At the user-level, we identify how human emotions are distributed and vary over time. At the ego-network level, we find that assortativity is only observed with respect to positive moods. This observation allows us to introduce emotional balance, the "dual'' of structural balance theory. We show that emotional balance has a natural connection to structural balance theory. At the community-level, we find that community members are emotionally-similar and that this similarity is stronger in smaller communities. Structural properties of communities, such as their sparseness or isolatedness, are also connected to the emotions of their members. At the whole-network level, we show that there is a tight connection between the global structure of a network and the emotions of its members. As a result, we demonstrate how one can accurately predict the proportion of positive/negative users within a network by only looking at the network structure. Based on our observations, we propose the Emotional-Tie model – a network model that can simulate the formation of friendships based on emotions. This model generates graphs that exhibit both patterns of human emotions identified in this work and those observed in real-world social networks, such as having a high clustering coefficient. Our findings can help better understand the interplay between emotions and social ties.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Understanding the role emotions play in social interactions has been a central research question in the social sciences. However, the challenge of obtaining large-scale data on human emotions has left the most fundamental questions on emotions less explored: How do emotions vary across individuals, evolve over time, and are connected to social ties?We address these questions using a large-scale dataset of users that contains both their emotions and social ties. Using this dataset, we identify patterns of human emotions on five different network levels, starting from the user-level and moving up to the whole-network level. At the user-level, we identify how human emotions are distributed and vary over time. At the ego-network level, we find that assortativity is only observed with respect to positive moods. This observation allows us to introduce emotional balance, the "dual'' of structural balance theory. We show that emotional balance has a natural connection to structural balance theory. At the community-level, we find that community members are emotionally-similar and that this similarity is stronger in smaller communities. Structural properties of communities, such as their sparseness or isolatedness, are also connected to the emotions of their members. At the whole-network level, we show that there is a tight connection between the global structure of a network and the emotions of its members. As a result, we demonstrate how one can accurately predict the proportion of positive/negative users within a network by only looking at the network structure. Based on our observations, we propose the Emotional-Tie model – a network model that can simulate the formation of friendships based on emotions. This model generates graphs that exhibit both patterns of human emotions identified in this work and those observed in real-world social networks, such as having a high clustering coefficient. Our findings can help better understand the interplay between emotions and social ties.
Zafarani, Reza; Liu, Huan
User identification across social media Miscellaneous
2017, (US Patent 9,544,381).
@misc{zafarani2017user,
title = {User identification across social media},
author = {Reza Zafarani and Huan Liu},
year = {2017},
date = {2017-01-01},
publisher = {Google Patents},
note = {US Patent 9,544,381},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
2016
Liu, Huan; Morstatter, Fred; Tang, Jiliang; Zafarani, Reza
The good, the bad, and the ugly: uncovering novel research opportunities in social media mining Journal Article
In: International Journal of Data Science and Analytics, vol. 1, no. 3-4, pp. 137–143, 2016.
@article{liu2016good,
title = {The good, the bad, and the ugly: uncovering novel research opportunities in social media mining},
author = {Huan Liu and Fred Morstatter and Jiliang Tang and Reza Zafarani},
year = {2016},
date = {2016-01-01},
journal = {International Journal of Data Science and Analytics},
volume = {1},
number = {3-4},
pages = {137–143},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Zafarani, Reza; Liu, Huan
Users joining multiple sites: Friendship and popularity variations across sites Journal Article
In: Information Fusion, vol. 28, pp. 83-89, 2016, ISSN: 1566-2535.
@article{zafarani2016users,
title = {Users joining multiple sites: Friendship and popularity variations across sites},
author = {Reza Zafarani and Huan Liu},
url = {https://www.sciencedirect.com/science/article/pii/S1566253515000676},
doi = {https://doi.org/10.1016/j.inffus.2015.07.002},
issn = {1566-2535},
year = {2016},
date = {2016-01-01},
journal = {Information Fusion},
volume = {28},
pages = {83-89},
abstract = {Our social media experience is no longer limited to a single site. We use different social media sites for different purposes and our information on each site is often partial. By collecting complementary information for the same individual across sites, one can better profile users. These profiles can help improve online services such as advertising or recommendation across sites. To combine complementary information across sites, it is critical to understand how information for the same individual varies across sites. In this study, we aim to understand how two fundamental properties of users vary across social media sites. First, we study how user friendship behavior varies across sites. Our findings show how friend distributions for individuals change as they join new sites. Next, we analyze how user popularity changes across sites as individuals join different sites. We evaluate our findings and demonstrate how our findings can be employed to predict how popular users are likely to be on new sites they join.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Our social media experience is no longer limited to a single site. We use different social media sites for different purposes and our information on each site is often partial. By collecting complementary information for the same individual across sites, one can better profile users. These profiles can help improve online services such as advertising or recommendation across sites. To combine complementary information across sites, it is critical to understand how information for the same individual varies across sites. In this study, we aim to understand how two fundamental properties of users vary across social media sites. First, we study how user friendship behavior varies across sites. Our findings show how friend distributions for individuals change as they join new sites. Next, we analyze how user popularity changes across sites as individuals join different sites. We evaluate our findings and demonstrate how our findings can be employed to predict how popular users are likely to be on new sites they join.
2015
Zafarani, Reza; Tang, Lei; Liu, Huan
User Identification Across Social Media Journal Article
In: ACM Transactions on Knowledge Discovery from Data (TKDD), vol. 10, no. 2, 2015, ISSN: 1556-4681.
@article{zafarani2015user,
title = {User Identification Across Social Media},
author = {Reza Zafarani and Lei Tang and Huan Liu},
url = {https://doi.org/10.1145/2747880},
doi = {10.1145/2747880},
issn = {1556-4681},
year = {2015},
date = {2015-10-01},
journal = {ACM Transactions on Knowledge Discovery from Data (TKDD)},
volume = {10},
number = {2},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {People use various social media sites for different purposes. The information on each site is often partial. When sources of complementary information are integrated, a better profile of a user can be built. This profile can help improve online services such as advertising across sites. To integrate these sources of information, it is necessary to identify individuals across social media sites. This paper aims to address the cross-media user identification problem. We provide evidence on the existence of a mapping among identities of individuals across social media sites, study the feasibility of finding this mapping, and illustrate and develop means for finding this mapping. Our studies show that effective approaches that exploit information redundancies due to users’ unique behavioral patterns can be utilized to find such a mapping. This study paves the way for analysis and mining across social networking sites, and facilitates the creation of novel online services across sites. In particular, recommending friends and advertising across networks, analyzing information diffusion across sites, and studying specific user behavior such as user migration across sites in social media are one of the many areas that can benefit from the results of this study.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
People use various social media sites for different purposes. The information on each site is often partial. When sources of complementary information are integrated, a better profile of a user can be built. This profile can help improve online services such as advertising across sites. To integrate these sources of information, it is necessary to identify individuals across social media sites. This paper aims to address the cross-media user identification problem. We provide evidence on the existence of a mapping among identities of individuals across social media sites, study the feasibility of finding this mapping, and illustrate and develop means for finding this mapping. Our studies show that effective approaches that exploit information redundancies due to users’ unique behavioral patterns can be utilized to find such a mapping. This study paves the way for analysis and mining across social networking sites, and facilitates the creation of novel online services across sites. In particular, recommending friends and advertising across networks, analyzing information diffusion across sites, and studying specific user behavior such as user migration across sites in social media are one of the many areas that can benefit from the results of this study.
Zafarani, Reza; Liu, Huan
Evaluation without Ground Truth in Social Media Research Journal Article
In: Communications of the ACM, vol. 58, no. 6, pp. 54–60, 2015, ISSN: 0001-0782.
@article{zafarani2015evaluation,
title = {Evaluation without Ground Truth in Social Media Research},
author = {Reza Zafarani and Huan Liu},
url = {https://doi.org/10.1145/2666680},
doi = {10.1145/2666680},
issn = {0001-0782},
year = {2015},
date = {2015-05-01},
journal = {Communications of the ACM},
volume = {58},
number = {6},
pages = {54–60},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
abstract = {Even without it, some ingenious methods can be developed to help verify users' social media behavioral patterns.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Even without it, some ingenious methods can be developed to help verify users' social media behavioral patterns.