運用社群演變序列偵測事件

Concept-Based Event Identification from Social Streams Using Evolving Social Graph Sequences

10.6843/NTHU.2014.00077

彭以程

偵測事件 ； 演變序列 ； 社群網路 ； Event Identification ； Concept-based Evolving Graph Sequences ； Social Network

清華大學資訊系統與應用研究所學位論文

2014年

碩士

陳宜欣

英文

21世紀的人們，越來越依賴社群網站。使用者在社群網站上發布或分享的大量資料，往往反映了真實的事件。有些事件甚至比新聞媒體更早被揭露。本論文的目標在運用社群演變序列偵測事件。我們的方法是運用移動窗戶式的統計理論來擷取候選事件。接著，我們使用觀念式演變圖形序列來模擬資訊的傳遞，並且根據這個特性偵測候選事件是否為事件。實驗結果顯示我們能有效的偵測真實事件。

Social networks, which have become extremely popular in the 21st century, contain a tremendous amount of user-generated content about real-world events. This user-generated content relays real-world events as they happen, and sometimes even ahead of the newswire. The goal of this work is to identify events from social streams. The proposed model utilizes sliding-window-based statistical techniques to extract event candidates from social streams. Subsequently, the “Concept-based evolving graph sequences”(cEGS) approach is employed to verify information propagation trends of event candidates and to identify those events. The experimental results show the usefulness of our approach in identifying real-world events in social streams.

1. [1] J. Allan, editor. Topic Detection and Tracking: Event-based Information Organization.
   連結：
2. Kluwer Academic Publishers, 2002.
   連結：
3. [2] E. Bakshy, I. Rosenn, C. Marlow, and L. A. Adamic. The role of social networks in
   連結：
4. information diffusion. In Proceedings of World Wide Web, pages 519–528, 2012.
   連結：
5. [4] M. Bell. Sohaib athar’s tweets from the attack on osama bin laden. 2 May 2011.
   連結：
6. the social semantic web. In Semantic Web and Web Science, pages 75–87.
   連結：
7. [7] M. Granovetter. The strength of weak ties. The American Journal of Sociology,
   連結：
8. [8] H. Kwak, C. Lee, H. Park, and S. Moon. What is Twitter, a social network or a news
   連結：
9. [9] E. Kwan, P.-L. Hsu, J.-H. Liang, and Y.-S. Chen. Event identification for social
   連結：
10. streams using keyword-based evolving graph sequences. In Proceedings of The 2013
    連結：
11. IEEE/ACM International Conference on Social Networks Analysis and Mining, 2013.
    連結：
12. based on incremental topic modeling. In Software Engineering, Artificial Intelligence,
    連結：
13. Conference on, pages 73–76, 2012.
    連結：
14. [12] M. Naaman, J. Boase, and C.-H. Lai. Is it really about me? message content in
    連結：
15. social awareness streams. In Proceedings of Computer Supported Cooperative Work
    連結：
16. [13] Y. Ohsawa, N. E. Benson, and M. Yachida. Keygraph: Automatic indexing by cooccurrence
    連結：
17. [14] A.-M. Popescu and M. Pennacchiotti. Detecting controversial events from twitter. In
    連結：
18. management, pages 1873–1876, 2010.
    連結：
19. [15] T. Sakaki, M. Okazaki, and Y. Matsuo. Earthquake shakes twitter users: real-time
    連結：
20. event detection by social sensors. In Proceedings of the 19th international conference
    連結：
21. Conference on Advances in Geographic Information Systems, pages 42–51, 2009.
    連結：
22. [17] H. Sayyadi, M. Hurst, and A. Maykov. Event detection and tracking in social streams.
    連結：
23. In Proceedings of International AAAI Conference on Weblogs and Social Media,
    連結：
24. [18] E. Seo, P. Mohapatra, and T. Abdelzaher. Identifying rumors and their sources in
    連結：
25. social networks. In SPIE Defense, Security, and Sensing, pages 83891I–83891I, 2012.
    連結：
26. [23] J. M. Zacks and B. Tversky. Event structure in perception and conception. Psychological
    連結：
27. Bulletin, 127, 2001.
    連結：
28. [3] H. Becker, M. Naaman, and L. Gravano. Beyond trending topics: Real-world event
29. identification on twitter. In Proceedings of International AAAI Conference onWeblogs
30. and Social Media, 2011.
31. [5] M. Cataldi, L. Di Caro, and C. Schifanella. Emerging topic detection on twitter based
32. on temporal and social terms evaluation. In Proceedings of the Tenth International
33. Workshop on Multimedia Data Mining, page 4, 2010.
34. [6] T. Gottron, O. Radcke, and R. Pickhardt. On the temporal dynamics of influence on
35. 78:1360–1380, 1973.
36. media? In Proceedings of World Wide Web, 2010.
37. [10] H. Ma, B. Wang, and N. Li. A novel online event analysis framework for micro-blog
38. Networking and Parallel & Distributed Computing (SNPD), 2012 13th ACIS International
39. [11] R. Mihalcea and P. Tarau. Textrank: Bringing order into texts. In Proceedings of
40. Conference on Empirical Methods in Natural Language Processing, volume 4, 2004.
41. Companion, 2010.
42. graph based on building construction metaphor. In Research and Technology
43. Advances in Digital Libraries, 1998. ADL 98. Proceedings. IEEE International
44. Forum on, pages 12–18. IEEE, 1998.
45. Proceedings of the 19th ACM international conference on Information and knowledge
46. on World Wide Web, pages 851–860, 2010.
47. [16] J. Sankaranarayanan, H. Samet, B. E. Teitler, M. D. Lieberman, and J. Sperling. Twitterstand:
48. news in tweets. In Proceedings of the 17th ACM SIGSPATIAL International
49. 2009.
50. [19] Shuyo and Nakatani. Language detection library for java, 2010.
51. [20] Twitter. Twitter turns six, 21 March 2012.
52. [21] T. Wasserman. Twitter says it has 140 million users, 21 March 2012.
53. [22] J. Weng and B.-S. Lee. Event detection in twitter. In International Conference on
54. Weblogs and Social Media, 2011.