隨著科技的進步、商業成本考量以及現代人上網習慣改變，越來越多人使用Twitter、Facebook和MySpace等社群網站，使得社群行銷已經取代傳統病毒式行銷變成一門熱門的研究議題。與過去不同的是社群行銷對於資訊的傳播不在只是漫無目的地靠著目的使用者發送，而是尋找具有影響力的使用者傳達資訊，使得資訊傳播的速度以及效率達到最佳的狀態。
在本論文中，我們利用了社群行銷的概念提出了一個具有推估使用者影響力排名模型以利提升資訊傳播的速度以及效率。首先，我們搜尋特定關鍵字的相關文章來做情感分析以及分析其主題。接著利用文章間的關係以及對於主題的喜好程度，將文章的傳播流向組成一副資訊流地圖。最後，根據分析每位使用者在Twitter上的數據，我們將測試不同模型的結果，選擇出最適當的影響力排名組合，以期望能夠最符合現實世界的結果。

With the development of technology and the consideration of business cost and change of pace of people, more and more people use social network like twitter, facebook, myspace…etc. Social marketing has replaced traditional viral marketing and becoming a hot research issue. What is different from the past is that information-transferring on social marketing is not based on random users but finding the influential users, it could make sure the speed up the information-transferring and efficiency attain the best result.
In the thesis, we use the concept of social marketing to propose a user influential ability ranking model to improve the speed of information-transferring and efficiency. At first, we search the relational tweets with specific key terms to analyze the topics and sentiment score. And we use the relationship among tweets and preference degree to create an information flow map. Finally we analyze user profile on twitter to test the different influential models scores and choosing the suitable model to expect in line with actual situation.

[1] Bradley, M. M., &Lang, P. J. (1999a).Affective norms for English words (ANEW): Instruction manual and affective ratings. Gainesville, FL: Center for Research in
Psychophysiology, University of Florida.
[2] Thelwall, M., Buckley, K., Paltoglou, G., Cai, D. and Kappas, A. (2010), Sentiment strength detection in short informal text. J. Am. Soc. Inf. Sci., 61: 2544–2558. doi:10.1002/asi.21416
[3] Thelwall, M., Buckley, K. and Paltoglou, G. (2012), Sentiment strength detection for the social web. J. Am. Soc. Inf. Sci., 63: 163–173. doi: 10.1002/asi.21662
[4] Thelwall, M., & Buckley, K. (in press). Topic-based sentiment analysis for the SocialWeb: The role of mood and issue-related words. Journal of the American Society for Information Science and Technology
[5] Page, Lawrence and Brin, Sergey and Motwani, Rajeev and Winograd, Terry (1999) The PageRank Citation Ranking: Bringing Order to the Web. Technical Report. Stanford InfoLab..
[6] Thomas Roelleke and Jun Wang. 2008. TF-IDF uncovered: a study of theories and probabilities. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval (SIGIR '08). ACM, New York, NY,USA,435-442.DOI=10.1145/1390334.1390409 http://doi.acm.org/10.1145/1390334.1390409
[7] Adar, E.; Adamic, L.A.; , "Tracking information epidemics in blogspace," Web Intelligence, 2005. Proceedings. The 2005 IEEE/WIC/ACM International Conference on , vol., no., pp. 207- 214, 19-22 Sept. 2005 doi: 10.1109/WI.2005.151
[8] Kahn, J. H., Tobin, R. M., Massey, A. E., & Anderson, J. A. (2007). Measuring emotional expression with the Linguistic Inquiry and Word Count. American Journal of Psychology,120, 263-286
[9] http://wefollow.com/
[10] http://twitaholic.com/
[11] http://stats.brandtweet.com/
[12] Manning, C.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)
[13] Kalervo Järvelin , Jaana Kekäläinen, IR evaluation methods for retrieving highly relevant documents, Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, p.41-48, July 24-28, 2000, Athens, Greece [doi>10.1145/345508.345545]
[14] Yong-Suk Kwon, Sang-Wook Kim, Sunju Park, Seung-Hwan Lim, and Jae Bum Lee. 2009. The information diffusion model in the blog world. In Proceedings of the 3rd Workshop on Social Network Mining and Analysis (SNA-KDD '09). ACM, New York, NY, USA, , Article 4 , 9 pages. DOI=10.1145/1731011.1731015 http://doi.acm.org/10.1145/1731011.1731015
[15] Florian Beil, Martin Ester, and Xiaowei Xu. 2002. Frequent term-based text clustering. InProceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '02). ACM, New York, NY, USA, 436-442. DOI=10.1145/775047.775110 http://doi.acm.org/10.1145/775047.775110