In this thesis, we have proposed a content-based method to identify users’ roles and find the role change patterns in a social network. Our proposed method doesn’t need to define role types in advance and allow a user to play multiple roles on a social network.
Our method provides a more general and flexible way to perform role analyses in social networks. Users’ behavior and content generated play an important role in characterizing users. Thus, the affectivity and recognition features in our model lead us to find more meaningful roles from different aspects. The recognition can help us to find the influential individuals, which implies that the content generated by users may be useful. The affectivity expresses the attitude of users to the group. Moreover, by introducing the concept of fuzzy sets to the proposed method, we allow a user to play multiple roles on a social network, not limited to just one.
The experimental results show that the proposed method finds various roles in social networks without using any pre-defined roles and can discover additional roles that haven’t been previously aware of. For example, kicker in Android is found unexpectedly. Compared with the method proposed by Agarwal et al. [1], our method can find two additional roles. The users of one of these roles who rarely publish articles but seek for information may be potential consumers. It is helpful for us to identify different roles of users and implement different policies to manage them.
In addition, we discover some interesting frequent RC patterns in Android and Obama. In Android, some users are likely to shift their roles to leader since they frequently discuss technology issues about Android, and learn more and more expertise from the fan group. Thus, their recognition increases with time. In Obama, even there are some users staunchly support the politician, some users may shift their roles from the role to the other roles with higher negative affectivity, which may be a warning sign for the politician.
In the future, we may extend our model to take dynamic social network properties
into consideration, and add some context conditions to our model. With the fast growth of social networks, we may extend our model to analyze a large scale of social networks. We may also broaden the scope from fan groups to enterprise groups and compare the roles found from fan groups with those found from enterprise groups.
Moreover, enhancing the content analysis in text and analyzing the relationships between roles are another direction to extend our model.
References
[1] N. Agarwal, H. Liu, L. Tang, and P. S. Yu. 2008. Identifying the influential bloggers in a community. In Proceedings of the 1st ACM International Conference on Web Search and Data Mining, 207–218.
[2] M.A. Akaka and J. D. Chandler. 2011. Roles as resources: A social roles perspective of change in value networks. Marketing Theory, vol. 11, no. 3, 243–260.
[3] F. Benevenuto, T. Rodrigues, M. Cha, V. Almeida. 2009. Characterizing user behavior in online social networks. In Proceedings of the 9th ACM SIGCOMM Internet Measurement Conference, 49–62.
[4] F. Benevenuto, T. Rodrigues, V. Almeida, J. Almeida, M. Gonçalves. 2009.
Detecting spammers and content promoters in online video social networks. In Proceedings of the 32nd international ACM Conference on Research and Development in Information Retrieval, 620–627.
[5] J.C. Bezdeck, R. Ehrlich, and W. Full. 1984. FCM: Fuzzy C-Means Algorithm.
Computers and Geoscience, vol. 10, no. 2–3, 191–203.
[6] J.R. Blau, N. Goodman. 1991. Social Roles and Social Institutions: Essays in Honor of Rose Laub Coser. Westview Press: Boulder.
[7] F. Bodendorf, C. Kaiser. 2009. Detecting opinion leaders and trends in online social networks. In Proceedings of the 2nd ACM Workshop on Social Web Search and Mining, 65–68.
[8] M. M. Bradley and P. J. Lang. 1999. Affective norms for English words (ANEW): Instruction manual and affective ratings. Technical Report C-1. The Center for Research in Psychophysiology, University of Florida.
[9] P.L. Callero. 1994. From role-playing to role-using. Understanding role as a resource. Social Psychology Quarterly, vol. 57, 247–256.
[10] M. Fazeen, R. Dantu, P. Guturu. 2011. Identification of leaders, lurkers, associates and spammers in a social network: Context-dependent and
context-independent approaches. Social Network Analysis and Mining, vol. 1, 241–254.
[11] D. Fisher, M. Smith, and H.T. Welser. 2006. You are who you talk to:
Detecting roles in Usenet newsgroups. In Proceedings of the 39th Hawaii International Conference on System Sciences, 59–68.
[12] S. Fournier and L. Lee. 2009. Getting brand communities right. Harvard Business Review, April, 105–111.
[13] N.P. Garg, S. Favre, H. Salamin, D.H. Tür, A. Vinciarelli. 2008. Role recognition for meeting participants: An approach based on lexical information and social network analysis. In Proceedings of the 16th ACM International Conference on Multimedia, 693–696.
[14] E. Gleave, H. T. Welser, T. M. Lento, and M. A. Smith. 2009. A conceptual and operational definition of ‘social role’ in online community. In Proceedings of the 42nd Hawaii International Conference on System Sciences, 1–11.
[15] S.A. Golder. 2003. A Typology of Social Roles in Usenet. Master Thesis, Department of Linguistics, Harvard University.
[16] A. Goyal, F. Bonchi, and L. V.S. Lakshmanan. 2008. Discovering leaders from community actions. In Proceeding of the 17th ACM Conference on Information and Knowledge Management, 499–508.
[17] InsightXplorer: http://news.ixresearch.com/.
[18] S. Jamali and H. Rangwala. 2009. Digging digg: Comment mining, popularity prediction, and social network analysis. In Proceedings of International Conference on Web Information Systems and Mining, 32–38.
[19] D. Kempe, J. Kleinberg, and E. Tardos. 2003. Maximizing the spread of influence through a social network. In Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 137–146.
[20] D. Kempe, J. Kleinberg, and E. Tardos. 2005. Influential nodes in a diffusion model for social networks. In Proceedings of the 32nd International Colloquium
on Automata, Languages and Programming, 1127–1138.
[21] V.I. Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. Soviet Physics Doklady, vol. 10, 707–710.
[22] M. Maia, J. Almeida, and V. Almeida. 2008. Identifying user behavior in online social networks. In Proceedings of the 1st Workshop on Social Network Systems, 1–6.
[23] A. McCallum, A. Corrada-Emmanuel, X. Wang. 2005. Topic and role discovery in social networks. In Proceedings of the 19th International Joint Conference on Artificial Intelligence, 786–791.
[24] J.C. Mitchell. 1969. Social Networks in Urban Situations: Analyses of Personal Relationships in Central African Towns. Manchester U. P: Manchester.
[25] M. Morzy. 2009. On mining and social role discovery in Internet forums. In Proceedings of International Workshop on Social Informatics (SOCINFO), 74–
79.
[26] M. Naaman, J. Boase, C. Lai. 2010. Is it really about me? Message content in social awareness streams. In Proceedings of the ACM Conference on Computer Supported Cooperative Work, 189–192.
[27] F. Nielsen. 2011. A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. In Proceedings of the ESWC2011 Workshop on Making Sense of Microposts, CoRR, 93–98.
[28] T. Parsons.1951. The Social System. Glencoe, IL: Free Press.
[29] J. Pei, J. Han, B. Mortazavi-Asl, H. Pinto, Q. Chen, U. Dayal, and M. C. Hsu.
2001. PrefixSpan: Mining sequential patterns efficiently by prefix-projected pattern growth. In Proceedings of International Conference on Data Engineering, 215–224.
[30] F. Skopik, H.L. Truong, S. Dustdar. 2009. Trust and reputation mining in professional virtual communities. In Proceedings of International Conference on Web Engineering. Lecture Notes in Computer Science (LNCS), vol. 5648,
76–90.
[31] M. Trusov, A. V. Bodapati, and R. E. Bucklin. 2010. Determining influential users in Internet social networks. Journal of Marketing Research, vol. 47, no. 4, 643–658.
[32] T.C. Turner, M. Smith, D. Fisher, and H.T. Welser. 2005. Picturing Usenet:
Mapping computer-mediated collective action. Journal of Computer Mediated Communication, vol. 10, no. 4, article 7.
[33] P. Velardi, R. Navigli, A. Cucchiarelli, F.D. Antonio. 2008. A new content-based model for social network analysis. In Proceedings of the IEEE International Conference on Semantic Computing, 18–25.
[34] H.T. Welser, D. Cosley, G. Kossinets, A. Lin, F. Dokshin, G. Gay, M. Smith.
2011. Finding social roles in Wikipedia. In Proceedings of the iConference, 122–129.
[35] H.T. Welser, E. Gleave, D. Fisher, and M. Smith. 2007. Visualizing the signatures of social roles in online discussion groups. The Journal of Social Structure, vol. 8, no. 2, 1–32.
[36] H.T. Welser, E. Gleave, V. Barash, M. Smith, J. Meckes. 2009. Whither the experts? Social affordances and the cultivation of experts in community Q&A systems. In Proceedings of International Conference on Computational Science and Engineering, 450–455.
[37] Z. Wu and C. Chen. 2011. User classification and relationship detecting on social network site. In Proceedings of International Conference on Control, Automation and Systems Engineering, 1–4.
[38] T. Zhu, B. Wang, B. Wu, and C. Zhu. 2011. Role defining using behavior-based clustering in telecommunication network. Expert Systems with Applications, vol. 38, 3902–3908.