透過關鍵字動態影響力模型偵測社群平台使用者興趣

A Dynamic Influence Keyword Model for Identifying Implicit User Interests on Social Networks

吳少辰(Wu, Shaochen)

指導教授 ： 陳宜欣

國立清華大學/電機資訊學院/資訊工程學系/碩士(2013年)

摘要

長久以來，使用者在社群平台上往往會不經意透露自己所感興趣的事物，包含心情、經驗及關注的議題。本篇論文試圖建立一個動態關鍵字興趣模型，用以計算每個興趣關鍵字對於使用者的影響力分數並進行排序，藉以臆測使用者可能的興趣。本研究結果與人為觀察使用者所發表的訊息進行興趣猜測的一致性高達91%，可謂本研究模型可以模擬類似人為思考模式以協助判別社群使用者興趣。

關鍵字

資料探勘 ； 使用者興趣偵測

並列摘要

User tends to reveal what they are interested in on the social networks but not always in a clear way. This paper provides a dynamic interest keyword model to know the influence of each interest aects the user. So that it can identify the possible interests of the user. The results shows 91% accordance that this model is competitive to human guessed interests by observation. This high accordance shows our proposed model is feasible.

參考文獻

[2] H. Bao and E. Y. Chang. Adheat: an in uence-based

Association for Computational Linguistics.

[7] J. Hannon, M. Bennett, and B. Smyth. Recommending twitter users to follow using content and collaborative ltering approaches. In Proceedings of the fourth ACM conference on Recommender systems, RecSys '10, pages 199{206, New York, NY, USA, 2010. ACM.

[9] P. Mylonas, D. Vallet, P. Castells, M. Fern Andez, and Y. Avrithis. Personalized information retrieval based on context and ontological knowledge. Knowl. Eng. Rev., 3(1):73{100, Mar. 2008.

[10] S. Piao and J. Whittle. A feasibility study on extracting twitter users' interests using nlp tools for