2015
Zafarani, Reza; Tang, Lei; Liu, Huan
User Identification across Social Media Journal Article
In: ACM Transactions on Knowledge Discovery from Data, 2015.
@article{reza2015user,
title = {User Identification across Social Media},
author = {Reza Zafarani and Lei Tang and Huan Liu},
url = {http://tkdd.acm.org/},
year = {2015},
date = {2015-10-01},
journal = {ACM Transactions on Knowledge Discovery from Data},
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, 2015.
@article{reza2015evaluation,
title = {Evaluation without Ground Truth in Social Media Research},
author = {Reza Zafarani and Huan Liu},
url = {http://cacm.acm.org/magazines/2015/6/187323-evaluation-without-ground-truth-in-social-media-research},
year = {2015},
date = {2015-06-01},
journal = {Communications of the ACM},
abstract = {With the rise of social media, user generated content has become available at an unprecedented scale. These massive collections of user generated content can help better understand billions of individuals. This data also enables novel scientific research in social sciences, anthropology, psychology, and economics at scale. Scientific research demands reproducible and independently verifiable findings. In social media research, scientific findings can be in form of behavioral patterns such as \textit{individuals commented on this Facebook post because of its quality.} To validate such patterns one can survey the individuals that exhibited the pattern to verify if the patterns truly captured their intentions. This type of validation is known as evaluation with ground truth in data mining. However, social media users are scattered all across the globe. With no face-to-face access to individuals on social media, is it even possible to perform evaluation for social media research? In other words, how can we verify that the user behavioral patterns found are the `true patterns' of these individuals?},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
With the rise of social media, user generated content has become available at an unprecedented scale. These massive collections of user generated content can help better understand billions of individuals. This data also enables novel scientific research in social sciences, anthropology, psychology, and economics at scale. Scientific research demands reproducible and independently verifiable findings. In social media research, scientific findings can be in form of behavioral patterns such as individuals commented on this Facebook post because of its quality. To validate such patterns one can survey the individuals that exhibited the pattern to verify if the patterns truly captured their intentions. This type of validation is known as evaluation with ground truth in data mining. However, social media users are scattered all across the globe. With no face-to-face access to individuals on social media, is it even possible to perform evaluation for social media research? In other words, how can we verify that the user behavioral patterns found are the `true patterns' of these individuals?
Sampson, Justin; Morstatter, Fred; Zafarani, Reza; Liu, Huan
Real-Time Crisis Mapping using Language Distribution Proceedings Article
In: Proceedings of the 2015 IEEE International Conference on Data Mining (ICDM), 2015.
@inproceedings{justin2015realtime,
title = {Real-Time Crisis Mapping using Language Distribution},
author = {Justin Sampson and Fred Morstatter and Reza Zafarani and Huan Liu},
url = {http://icdm2015.stonybrook.edu/},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 2015 IEEE International Conference on Data Mining (ICDM)},
abstract = {With the increase in GPS-enabled devices, social media sites, such as Twitter, are quickly becoming a prime outlet for timely geo-spatial data. Such data can be leveraged to aid in emergency response planning and recovery operations. Unfortunately, the information overload poses significant difficulty to the quick discovery and identification of emergency situation areas. The system tackles this challenge by providing real-time mapping of influence areas based on automatic analysis of the flow of discussion using language distributions. The workflow is then further enhanced through the addition of keyword surprise mapping which projects the general divergence map onto specific task-level keywords for precise and focused response.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
With the increase in GPS-enabled devices, social media sites, such as Twitter, are quickly becoming a prime outlet for timely geo-spatial data. Such data can be leveraged to aid in emergency response planning and recovery operations. Unfortunately, the information overload poses significant difficulty to the quick discovery and identification of emergency situation areas. The system tackles this challenge by providing real-time mapping of influence areas based on automatic analysis of the flow of discussion using language distributions. The workflow is then further enhanced through the addition of keyword surprise mapping which projects the general divergence map onto specific task-level keywords for precise and focused response.
Zafarani, Reza; Liu, Huan
10 Bits of Surprise: Detecting Malicious Users with Minimum Information Proceedings Article
In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM), 2015.
@inproceedings{reza2015bits,
title = {10 Bits of Surprise: Detecting Malicious Users with Minimum Information},
author = {Reza Zafarani and Huan Liu},
url = {http://www.cikm-2015.org/},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM)},
abstract = {Malicious users are a threat to many sites and defending against them demands innovative countermeasures. When malicious users join sites, they provide limited information about themselves. With this limited information, sites can find it difficult to distinguish between a malicious user and a normal user. In this study, we develop a methodology that identifies malicious users with limited information. As information provided by malicious users can vary, the proposed methodology utilizes minimum information to identify malicious users. It is shown that as little as 10 bits of information can help greatly in this challenging task. The experiments results verify that this methodology is effective in identifying malicious users in the realistic scenario of limited information availability.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Malicious users are a threat to many sites and defending against them demands innovative countermeasures. When malicious users join sites, they provide limited information about themselves. With this limited information, sites can find it difficult to distinguish between a malicious user and a normal user. In this study, we develop a methodology that identifies malicious users with limited information. As information provided by malicious users can vary, the proposed methodology utilizes minimum information to identify malicious users. It is shown that as little as 10 bits of information can help greatly in this challenging task. The experiments results verify that this methodology is effective in identifying malicious users in the realistic scenario of limited information availability.
Rajadesingan, Ashwin; Zafarani, Reza; Liu, Huan
Sarcasm Detection on Twitter: A Behavioral Modeling Approach Proceedings Article
In: Proceedings of the 8th ACM International Conference on Web Search and Data Mining (WSDM), 2015, (Dataset: http://bit.ly/SarcasmDetectionWSDM2015).
@inproceedings{ashwin2015sarcasm,
title = {Sarcasm Detection on Twitter: A Behavioral Modeling Approach},
author = {Ashwin Rajadesingan and Reza Zafarani and Huan Liu},
url = {http://www.wsdm-conference.org/2015/},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 8th ACM International Conference on Web Search and Data Mining (WSDM)},
abstract = {Sarcasm is a nuanced form of language in which individuals state the opposite of what is implied. With this intentional ambiguity, sarcasm detection has always been a challenging task, even for humans. Current approaches to automatic sarcasm detection rely primarily on lexical and linguistic cues. This paper aims to address the difficult task of sarcasm detection on Twitter by leveraging behavioral traits intrinsic to users expressing sarcasm. We identify such traits using the user's past tweets. We employ theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm. We evaluate our framework and demonstrate its efficiency in identifying sarcastic tweets.},
note = {Dataset: http://bit.ly/SarcasmDetectionWSDM2015},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sarcasm is a nuanced form of language in which individuals state the opposite of what is implied. With this intentional ambiguity, sarcasm detection has always been a challenging task, even for humans. Current approaches to automatic sarcasm detection rely primarily on lexical and linguistic cues. This paper aims to address the difficult task of sarcasm detection on Twitter by leveraging behavioral traits intrinsic to users expressing sarcasm. We identify such traits using the user's past tweets. We employ theories from behavioral and psychological studies to construct a behavioral modeling framework tuned for detecting sarcasm. We evaluate our framework and demonstrate its efficiency in identifying sarcastic tweets.
2014
Zafarani, Reza; Abbasi, Mohammad Ali; Liu, Huan
Social Media Mining: An Introduction Book
Cambridge University Press, 2014.
@book{reza2014social,
title = {Social Media Mining: An Introduction},
author = {Reza Zafarani and Mohammad Ali Abbasi and Huan Liu},
url = {http://www.cambridge.org/us/academic/subjects/computer-science/knowledge-management-databases-and-data-mining/social-media-mining-introduction},
year = {2014},
date = {2014-01-01},
publisher = {Cambridge University Press},
abstract = {The growth of social media over the last decade has revolutionized the way individuals interact and industries conduct business. Individuals produce data at an unprecedented rate by interacting, sharing, and consuming content through social media. Understanding and processing this new type of data to glean actionable patterns presents challenges and opportunities for interdisciplinary research, novel algorithms, and tool development. Social Media Mining integrates social media, social network analysis, and data mining to provide a convenient and coherent platform for students, practitioners, researchers, and project managers to understand the basics and potentials of social media mining. It introduces the unique problems arising from social media data and presents fundamental concepts, emerging issues, and effective algorithms for network analysis and data mining. Suitable for use in advanced undergraduate and beginning graduate courses as well as professional short courses, the text contains exercises of different degrees of difficulty that improve understanding and help apply concepts, principles, and methods in various scenarios of social media mining.},
keywords = {},
pubstate = {published},
tppubtype = {book}
}
The growth of social media over the last decade has revolutionized the way individuals interact and industries conduct business. Individuals produce data at an unprecedented rate by interacting, sharing, and consuming content through social media. Understanding and processing this new type of data to glean actionable patterns presents challenges and opportunities for interdisciplinary research, novel algorithms, and tool development. Social Media Mining integrates social media, social network analysis, and data mining to provide a convenient and coherent platform for students, practitioners, researchers, and project managers to understand the basics and potentials of social media mining. It introduces the unique problems arising from social media data and presents fundamental concepts, emerging issues, and effective algorithms for network analysis and data mining. Suitable for use in advanced undergraduate and beginning graduate courses as well as professional short courses, the text contains exercises of different degrees of difficulty that improve understanding and help apply concepts, principles, and methods in various scenarios of social media mining.
Zafarani, Reza; Liu, Huan
Behavior Analysis in Social Media Journal Article
In: IEEE Intelligent Systems, vol. 29, no. 4, pp. 9–11, 2014.
@article{reza2014behavior,
title = {Behavior Analysis in Social Media},
author = {Reza Zafarani and Huan Liu},
year = {2014},
date = {2014-01-01},
journal = {IEEE Intelligent Systems},
volume = {29},
number = {4},
pages = {9–11},
abstract = {With the rise of social media, information sharing has been democratized. As a result, users are given opportunities to exhibit different behaviors such as sharing, posting, liking, commenting, and befriending conveniently and on a daily basis. By analyzing behaviors observed on social media, we can categorize these behaviors into individual and collective behavior. Individual behavior is exhibited by a single user, whereas collective behavior is observed when a group of users behave together. For instance, users using the same hashtag on Twitter or migrating to another social media site are examples of collective behavior. User activities on social media generate behavioral data, which is massive, expansive, and indicative of user preferences, interests, opinions, and relationships. This behavioral data provides a new lens through which we can observe and analyze individual and collective behaviors of users.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
With the rise of social media, information sharing has been democratized. As a result, users are given opportunities to exhibit different behaviors such as sharing, posting, liking, commenting, and befriending conveniently and on a daily basis. By analyzing behaviors observed on social media, we can categorize these behaviors into individual and collective behavior. Individual behavior is exhibited by a single user, whereas collective behavior is observed when a group of users behave together. For instance, users using the same hashtag on Twitter or migrating to another social media site are examples of collective behavior. User activities on social media generate behavioral data, which is massive, expansive, and indicative of user preferences, interests, opinions, and relationships. This behavioral data provides a new lens through which we can observe and analyze individual and collective behaviors of users.
Abbasi, Mohammad Ali; Zafarani, Reza; Tang, Jiliang; Liu, Huan
Am I More Similar to My Followers or Followees? Analyzing Homophily Effect in Directed Social Networks Proceedings Article
In: Proceedings of the 25th ACM Conference on Hypertext and Social Media (HT), 2014.
@inproceedings{mohammad2014more,
title = {Am I More Similar to My Followers or Followees? Analyzing Homophily Effect in Directed Social Networks},
author = {Mohammad Ali Abbasi and Reza Zafarani and Jiliang Tang and Huan Liu},
url = {http://ht.acm.org/ht2014/},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the 25th ACM Conference on Hypertext and Social Media (HT)},
abstract = {Homophily is the theory behind the formation of social ties between individuals with similar characteristics or interests. Based on homophily, in a social network it is expected to observe a higher degree of homogeneity among connected than disconnected people. Many researchers use this simple yet effective principal to infer users' missing information and interests based on the information provided by their neighbors. In a directed social network, the neighbors can be further divided into followers and followees. In this work, we investigate the homophily effect in a directed network. To explore the homophily effect in a directed network, we study if a user's personal preferences can be inferred from those of users connected to her (followers or followees). We also study the effectiveness of each of these two groups on prediction one's preferences.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Homophily is the theory behind the formation of social ties between individuals with similar characteristics or interests. Based on homophily, in a social network it is expected to observe a higher degree of homogeneity among connected than disconnected people. Many researchers use this simple yet effective principal to infer users' missing information and interests based on the information provided by their neighbors. In a directed social network, the neighbors can be further divided into followers and followees. In this work, we investigate the homophily effect in a directed network. To explore the homophily effect in a directed network, we study if a user's personal preferences can be inferred from those of users connected to her (followers or followees). We also study the effectiveness of each of these two groups on prediction one's preferences.
Zafarani, Reza; Liu, Huan
Users Joining Multiple Sites: Distributions and Patterns Proceedings Article
In: Proceedings of the 8th International AAAI Conference on Web and Social Media (ICWSM), 2014.
@inproceedings{reza2014users,
title = {Users Joining Multiple Sites: Distributions and Patterns},
author = {Reza Zafarani and Huan Liu},
url = {http://icwsm.org/2014/},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the 8th International AAAI Conference on Web and Social Media (ICWSM)},
abstract = {The rise of social media has led to an explosion in the number of possible sites users can join. However, this same profusion of social media sites has made it nearly impossible for users to actively engage in all of them simultaneously. Accordingly, users must make choices about which sites to use or to neglect. In this paper, we study users that have joined multiple sites. We study how individuals are distributed across sites, the way they select sites to join, and behavioral patterns they exhibit while selecting sites. Our study demonstrates that while users have a tendency to join the most popular or trendiest sites, this does not fully explain users' selections. We demonstrate that peer pressure also influences the decisions users make about joining emerging sites.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The rise of social media has led to an explosion in the number of possible sites users can join. However, this same profusion of social media sites has made it nearly impossible for users to actively engage in all of them simultaneously. Accordingly, users must make choices about which sites to use or to neglect. In this paper, we study users that have joined multiple sites. We study how individuals are distributed across sites, the way they select sites to join, and behavioral patterns they exhibit while selecting sites. Our study demonstrates that while users have a tendency to join the most popular or trendiest sites, this does not fully explain users' selections. We demonstrate that peer pressure also influences the decisions users make about joining emerging sites.
Zafarani, Reza; Liu, Huan
Finding Friends on a New Site Using Minimum Information Proceedings Article
In: Proceedings of the 2014 SIAM International Conference on Data Mining (SDM), 2014.
@inproceedings{reza2014finding,
title = {Finding Friends on a New Site Using Minimum Information},
author = {Reza Zafarani and Huan Liu},
url = {http://www.siam.org/meetings/sdm14/},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings of the 2014 SIAM International Conference on Data Mining (SDM)},
abstract = {With the emergence of numerous social media sites, individuals, with their limited time, often face a dilemma of choosing a few sites over others. Users prefer more engaging sites, where they can find familiar faces such as friends, relatives, or colleagues. Link prediction methods help find friends using link or content information. Unfortunately, whenever users join any site, they have no friends or any content generated. In this case, sites have no chance other than recommending random influential users to individuals hoping that users by befriending them create sufficient information for link prediction techniques to recommend meaningful friends. In this study, by considering social forces that form friendships, namely, influence, homophily, and confounding, and by employing minimum information available for users, we demonstrate how one can significantly improve random predictions without link or content information. In addition, contrary to the common belief that similarity between individuals is the essence of forming friendships, we show that it is the similarity that one exhibits to the friends of another individual that plays a more decisive role in predicting their future friendship.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
With the emergence of numerous social media sites, individuals, with their limited time, often face a dilemma of choosing a few sites over others. Users prefer more engaging sites, where they can find familiar faces such as friends, relatives, or colleagues. Link prediction methods help find friends using link or content information. Unfortunately, whenever users join any site, they have no friends or any content generated. In this case, sites have no chance other than recommending random influential users to individuals hoping that users by befriending them create sufficient information for link prediction techniques to recommend meaningful friends. In this study, by considering social forces that form friendships, namely, influence, homophily, and confounding, and by employing minimum information available for users, we demonstrate how one can significantly improve random predictions without link or content information. In addition, contrary to the common belief that similarity between individuals is the essence of forming friendships, we show that it is the similarity that one exhibits to the friends of another individual that plays a more decisive role in predicting their future friendship.
2013
Zafarani, Reza; Liu, Huan
Connecting Users across Social Media Sites: A Behavioral-Modeling Approach Proceedings Article
In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp. 41–49, 2013.
@inproceedings{reza2013connecting,
title = {Connecting Users across Social Media Sites: A Behavioral-Modeling Approach},
author = {Reza Zafarani and Huan Liu},
url = {http://dl.acm.org/citation.cfm?id=2487648},
year = {2013},
date = {2013-01-01},
booktitle = {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)},
pages = {41–49},
abstract = {People use various social media for different purposes. The information on an individual site is often incomplete. When sources of complementary information are integrated, a better profile of a user can be built to improve online services such as verifying online information. 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 introduce a methodology (MOBIUS) for finding a mapping among identities of individuals across social media sites. It consists of three key components: the first component identifies users' unique behavioral patterns that lead to information redundancies across sites; the second component constructs features that exploit information redundancies due to these behavioral patterns; and the third component employs machine learning for effective user identification. We formally define the cross-media user identification problem and show that MOBIUS is effective in identifying users across social media sites. This study paves the way for analysis and mining across social media sites, and facilitates the creation of novel online services across sites.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
People use various social media for different purposes. The information on an individual site is often incomplete. When sources of complementary information are integrated, a better profile of a user can be built to improve online services such as verifying online information. 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 introduce a methodology (MOBIUS) for finding a mapping among identities of individuals across social media sites. It consists of three key components: the first component identifies users' unique behavioral patterns that lead to information redundancies across sites; the second component constructs features that exploit information redundancies due to these behavioral patterns; and the third component employs machine learning for effective user identification. We formally define the cross-media user identification problem and show that MOBIUS is effective in identifying users across social media sites. This study paves the way for analysis and mining across social media sites, and facilitates the creation of novel online services across sites.
Kumar, Shamanth; Morstatter, Fred; Zafarani, Reza; Liu, Huan
Whom Should I Follow? Identifying Relevant Users in Crisis Proceedings Article
In: Proceedings of the 24th ACM Conference on Hypertext and Social Media (HT), 2013.
@inproceedings{shamanth2013whom,
title = {Whom Should I Follow? Identifying Relevant Users in Crisis},
author = {Shamanth Kumar and Fred Morstatter and Reza Zafarani and Huan Liu},
url = {http://dl.acm.org/citation.cfm?id=2481507},
year = {2013},
date = {2013-01-01},
booktitle = {Proceedings of the 24th ACM Conference on Hypertext and Social Media (HT)},
abstract = {Social media is gaining popularity as a medium of communication before, during, and after crises. In several recent disasters, it has become evident that social media sites like Twitter and Facebook are an important source of information, and in cases they have even assisted in relief efforts. We propose a novel approach to identify a subset of active users during a crisis who can be tracked for fast access to information. Using a Twitter dataset that consists of 12.9 million tweets from 5 countries that are part of the "Arab Spring" movement, we show how instant information access can be achieved by user identification along two dimensions: user's location and the user's affinity towards topics of discussion. Through evaluations, we demonstrate that users selected by our approach generate more information and the quality of the information is better than that of users identified using state-of-the-art techniques.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Social media is gaining popularity as a medium of communication before, during, and after crises. In several recent disasters, it has become evident that social media sites like Twitter and Facebook are an important source of information, and in cases they have even assisted in relief efforts. We propose a novel approach to identify a subset of active users during a crisis who can be tracked for fast access to information. Using a Twitter dataset that consists of 12.9 million tweets from 5 countries that are part of the "Arab Spring" movement, we show how instant information access can be achieved by user identification along two dimensions: user's location and the user's affinity towards topics of discussion. Through evaluations, we demonstrate that users selected by our approach generate more information and the quality of the information is better than that of users identified using state-of-the-art techniques.
Abbasi, Mohammad Ali; Liu, Huan; Zafarani, Reza
Social Media Mining: Fundamental Issues and Challenges Proceedings Article
In: Proceedings of the 2013 IEEE International Conference on Data Mining (ICDM), 2013.
@inproceedings{mohammad2013social,
title = {Social Media Mining: Fundamental Issues and Challenges},
author = {Mohammad Ali Abbasi and Huan Liu and Reza Zafarani},
year = {2013},
date = {2013-01-01},
booktitle = {Proceedings of the 2013 IEEE International Conference on Data Mining (ICDM)},
abstract = {Social media generates massive amounts of user-generated-content data. Such data differs from classic data and poses new challenges to data mining. This tutorial presents fundamental issues of social media mining, ranging from network representation to influence/diffusion modeling, elaborate state-of-the-art approaches of processing and analyzing social media data, and show how to utilize patterns to real-world applications, such as recommendation and behavior analytics. The tutorials designed for researchers, students and scholars interested in studying social media and social networks. No prerequisite is required for ICDM participants to attend this tutorial.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Social media generates massive amounts of user-generated-content data. Such data differs from classic data and poses new challenges to data mining. This tutorial presents fundamental issues of social media mining, ranging from network representation to influence/diffusion modeling, elaborate state-of-the-art approaches of processing and analyzing social media data, and show how to utilize patterns to real-world applications, such as recommendation and behavior analytics. The tutorials designed for researchers, students and scholars interested in studying social media and social networks. No prerequisite is required for ICDM participants to attend this tutorial.
2012
Barbier, Geoffrey; Zafarani, Reza; Gao, Huiji; Fung, Gabriel; Liu, Huan
Maximizing Benefits from Crowdsourced Data Journal Article
In: Computational and Mathematical Organization Theory, vol. 18, no. 3, pp. 257–279, 2012.
@article{geoffrey2012maximizing,
title = {Maximizing Benefits from Crowdsourced Data},
author = {Geoffrey Barbier and Reza Zafarani and Huiji Gao and Gabriel Fung and Huan Liu},
url = {http://link.springer.com/article/10.1007%2Fs10588-012-9121-2#page-1},
year = {2012},
date = {2012-01-01},
journal = {Computational and Mathematical Organization Theory},
volume = {18},
number = {3},
pages = {257–279},
abstract = {Crowds of people can solve some problems faster than individuals or small groups. A crowd can also rapidly generate data about circumstances affecting the crowd itself. This crowdsourced data can be leveraged to benefit the crowd by providing information or solutions faster than traditional means. However, the crowdsourced data can hardly be used directly to yield usable information. Intelligently analyzing and processing crowdsourced information can help prepare data to maximize the usable information, thus returning the benefit to the crowd. This article highlights challenges and investigates opportunities associated with mining crowdsourced data to yield useful information, as well as details how crowdsource information and technologies can be used for response-coordination when needed, and finally suggests related areas for future research.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Crowds of people can solve some problems faster than individuals or small groups. A crowd can also rapidly generate data about circumstances affecting the crowd itself. This crowdsourced data can be leveraged to benefit the crowd by providing information or solutions faster than traditional means. However, the crowdsourced data can hardly be used directly to yield usable information. Intelligently analyzing and processing crowdsourced information can help prepare data to maximize the usable information, thus returning the benefit to the crowd. This article highlights challenges and investigates opportunities associated with mining crowdsourced data to yield useful information, as well as details how crowdsource information and technologies can be used for response-coordination when needed, and finally suggests related areas for future research.
Agarwal, Nitin; Kumar, Shamanth; Gao, Huiji; Zafarani, Reza; Liu, Huan
Analyzing Behavior of the Influentials across Social Media Book Section
In: Cao, Longbing; Yu, Philip S. (Ed.): Behavior Computing: Modeling, Analysis, Mining and Decision, Springer London, London, 2012.
@incollection{nitin2012analyzing,
title = {Analyzing Behavior of the Influentials across Social Media},
author = {Nitin Agarwal and Shamanth Kumar and Huiji Gao and Reza Zafarani and Huan Liu},
editor = {Longbing Cao and Philip S. Yu},
url = {http://link.springer.com/chapter/10.1007%2F978-1-4471-2969-1_1#page-1},
year = {2012},
date = {2012-01-01},
booktitle = {Behavior Computing: Modeling, Analysis, Mining and Decision},
publisher = {Springer London},
address = {London},
abstract = {Studying these behavior patterns of users across different social media sites have many applications. If an individual exhibits same behavior on various social media sites then it can help predict his behavior on other social media websites by studying one social media site. Various social media sites can be clustered based on the behavior patterns of individuals. These clusters can help discover helpful and valuable trends. The activity of individuals can also help in explaining which social media sites are likely to get more activity for various groups of people. These patterns can be also used to explore marketing opportunities, study the movement of individuals on social media sites to focus on niche sites for unique opportunities.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Studying these behavior patterns of users across different social media sites have many applications. If an individual exhibits same behavior on various social media sites then it can help predict his behavior on other social media websites by studying one social media site. Various social media sites can be clustered based on the behavior patterns of individuals. These clusters can help discover helpful and valuable trends. The activity of individuals can also help in explaining which social media sites are likely to get more activity for various groups of people. These patterns can be also used to explore marketing opportunities, study the movement of individuals on social media sites to focus on niche sites for unique opportunities.
2011
Kumar, Shamanth; Zafarani, Reza; Liu, Huan
Understanding User Migration Patterns in Social Media Proceedings Article
In: Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI), 2011.
@inproceedings{shamanth2011understanding,
title = {Understanding User Migration Patterns in Social Media},
author = {Shamanth Kumar and Reza Zafarani and Huan Liu},
url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI11/paper/view/3664},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the 25th AAAI Conference on Artificial Intelligence (AAAI)},
abstract = {Incredible growth of the social web over the last decade has created a flurry of new social media sites for the users to choose from. Users with a lack of time and resources to engage on these sites must inevitably choose specific sites among them to remain active on. This choice more often than not leads to user migration, a well studied phenomenon in fields such as sociology and psychology. Users are the valuable assets for any site as they generate revenue and contribute to the growth of the site. Hence, It is essential for social media sites to establish and understand the reasons for user migration to prevent it. In this paper, we investigate whether people migrate, and if they do, how they migrate. We formalize site migration to help identify the migration between popular social media sites and determine clear patterns of migration between sites. This work suggests that it is feasible to study migration patterns. These patterns can help understand social media sites and gauge their popularity to improve business intelligence and revenue generation through the retention of users.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Incredible growth of the social web over the last decade has created a flurry of new social media sites for the users to choose from. Users with a lack of time and resources to engage on these sites must inevitably choose specific sites among them to remain active on. This choice more often than not leads to user migration, a well studied phenomenon in fields such as sociology and psychology. Users are the valuable assets for any site as they generate revenue and contribute to the growth of the site. Hence, It is essential for social media sites to establish and understand the reasons for user migration to prevent it. In this paper, we investigate whether people migrate, and if they do, how they migrate. We formalize site migration to help identify the migration between popular social media sites and determine clear patterns of migration between sites. This work suggests that it is feasible to study migration patterns. These patterns can help understand social media sites and gauge their popularity to improve business intelligence and revenue generation through the retention of users.
2010
Zafarani, Reza; Cole, William D.; Liu, Huan
Sentiment Propagation in Social Networks: A Case Study in LiveJournal Book Section
In: Chai, Sun-Ki; Salerno, John J.; Mabry, Patricia L. (Ed.): Advances in Social Computing, Springer, 2010.
@incollection{reza2010sentiment,
title = {Sentiment Propagation in Social Networks: A Case Study in LiveJournal},
author = {Reza Zafarani and William D. Cole and Huan Liu},
editor = {Sun-Ki Chai and John J. Salerno and Patricia L. Mabry},
url = {http://link.springer.com/chapter/10.1007%2F978-3-642-12079-4_52},
year = {2010},
date = {2010-01-01},
booktitle = {Advances in Social Computing},
publisher = {Springer},
abstract = {Social networking websites have facilitated a new style of communication through blogs, instant messaging, and various other techniques. Through collaboration, millions of users participate in millions of discussions every day. However, it is still difficult to determine the extent to which such discussions affect the emotions of the participants. We surmise that emotionally-oriented discussions may affect a given user.s general emotional bent and be reflected in other discussions he or she may initiate or participate in. It is in this way that emotion (or sentiment) may propagate through a network. In this paper, we analyze sentiment propagation in social networks, review the importance and challenges of such a study, and provide methodologies for measuring this kind of propagation. A case study has been conducted on a large dataset gathered from the LiveJournal social network. Experimental results are promising in revealing some aspects of the sentiment propagation taking place in social networks.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Social networking websites have facilitated a new style of communication through blogs, instant messaging, and various other techniques. Through collaboration, millions of users participate in millions of discussions every day. However, it is still difficult to determine the extent to which such discussions affect the emotions of the participants. We surmise that emotionally-oriented discussions may affect a given user.s general emotional bent and be reflected in other discussions he or she may initiate or participate in. It is in this way that emotion (or sentiment) may propagate through a network. In this paper, we analyze sentiment propagation in social networks, review the importance and challenges of such a study, and provide methodologies for measuring this kind of propagation. A case study has been conducted on a large dataset gathered from the LiveJournal social network. Experimental results are promising in revealing some aspects of the sentiment propagation taking place in social networks.
Kumar, Shamanth; Zafarani, Reza; Abbasi, Mohammad Ali; Barbier, Geoffrey; Liu, Huan
Convergence of Influential Bloggers for Topic Discovery in the Blogosphere Book Section
In: Chai, Sun-Ki; Salerno, John J.; Mabry, Patricia L. (Ed.): Advances in Social Computing, Springer, 2010.
@incollection{shamanth2010convergence,
title = {Convergence of Influential Bloggers for Topic Discovery in the Blogosphere},
author = {Shamanth Kumar and Reza Zafarani and Mohammad Ali Abbasi and Geoffrey Barbier and Huan Liu},
editor = {Sun-Ki Chai and John J. Salerno and Patricia L. Mabry},
url = {http://link.springer.com/chapter/10.1007/978-3-642-12079-4_51},
year = {2010},
date = {2010-01-01},
booktitle = {Advances in Social Computing},
publisher = {Springer},
abstract = {In this paper, we propose a novel approach to automatically detect .hot. or important topics of discussion in the blogosphere. The proposed approach is based on analyzing the activity of influential bloggers to determine specific points in time when there is a convergence amongst the influential bloggers in terms of their topic of discussion. The tool BlogTrackers, is used to identify influential bloggers and the Normalized Google Distance is used to define the similarity amongst the topics of discussion of influential bloggers. The key advantage of the proposed approach is its ability to automatically detect events which are important in the blogger community.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
In this paper, we propose a novel approach to automatically detect .hot. or important topics of discussion in the blogosphere. The proposed approach is based on analyzing the activity of influential bloggers to determine specific points in time when there is a convergence amongst the influential bloggers in terms of their topic of discussion. The tool BlogTrackers, is used to identify influential bloggers and the Normalized Google Distance is used to define the similarity amongst the topics of discussion of influential bloggers. The key advantage of the proposed approach is its ability to automatically detect events which are important in the blogger community.
2009
Zafarani, Reza; Liu, Huan
Connecting Corresponding Identities across Communities Proceedings Article
In: Proceedings of the Third International AAAI Conference on Web and Social Media (ICWSM), 2009.
@inproceedings{reza2009connecting,
title = {Connecting Corresponding Identities across Communities},
author = {Reza Zafarani and Huan Liu},
url = {http://aaai.org/ocs/index.php/ICWSM/09/paper/view/209},
year = {2009},
date = {2009-01-01},
booktitle = {Proceedings of the Third International AAAI Conference on Web and Social Media (ICWSM)},
abstract = {One of the most interesting challenges in the area of social computing and social media analysis is the so-called community analysis. A well known barrier in cross-community (multiple website) analysis is the disconnectedness of these websites. In this paper, our aim is to provide evidence on the existence of a mapping among identities across multiple communities, providing a method for connecting these websites. Our studies have shown that simple, yet effective approaches, which leverage social media's collective patterns can be utilized to find such a mapping. The employed methods successfully reveal this mapping with 66% accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
One of the most interesting challenges in the area of social computing and social media analysis is the so-called community analysis. A well known barrier in cross-community (multiple website) analysis is the disconnectedness of these websites. In this paper, our aim is to provide evidence on the existence of a mapping among identities across multiple communities, providing a method for connecting these websites. Our studies have shown that simple, yet effective approaches, which leverage social media's collective patterns can be utilized to find such a mapping. The employed methods successfully reveal this mapping with 66% accuracy.