基於社會行為之新聞分群研究

Clustering News Articles Based on Social Behavior

黃千籙(Chien-Lu Huang)

指導教授 ： 林敏勝

國立臺北科技大學/電資學院/電機工程系所/碩士(2014年)

https://doi.org/10.6841/NTUT.2014.00086

摘要

社群網路在我們的日常生活中扮演著越來越重要的角色，也漸漸改變社會行為方式。其結果造成社會行為越來越多元化，也就產生越來越多元化的社群。
本論文提出一些基於社會行為（例如：臉書新聞專頁上的點讚與留言行為）之新聞分群演算法。實驗結果顯示留言的社會行為較適用於新聞分群。

關鍵字

社群網路 ； 社會行為 ； 臉書 ； 分群演算法

並列摘要

The social network is playing a significant role in our daily life and is changing the ways of social behaviors. As a result, the more diverse social behaviors are, the more diverse social communities are.
This thesis proposes some algorithms for clustering news articles on Facebook pages based on the associated social behaviors, such as clicking the 'like' button or leaving comments on news articles. The experimental results show that the behavior of leaving comments is the more appropriate factor to be considered in clustering news articles.

並列關鍵字

Social network ； Social behavior ； Facebook ； Clustering algorithm

參考文獻

4.Naseem, R., Maqbool, O., & Muhammad, S. (2010, September). An improved similarity measure for binary features in software clustering. In Computational Intelligence, Modelling and Simulation (CIMSiM), 2010 Second International Conference on (pp. 111-116). IEEE.

8.Zeng, H. J., Wang, X. H., Chen, Z., Lu, H., & Ma, W. Y. (2003, November). CBC: Clustering based text classification requiring minimal labeled data. InData Mining, 2003. ICDM 2003. Third IEEE International Conference on (pp. 443-450). IEEE.

3.Howard Rheingold (1993). The Virtual Community: Homesteading on the Electronic Frontier. London: MIT Press.

5.C. J. V. Rijsbergen, Information Retrieval, 2 ed.: Butterworth-Heinemann, 1979.

10.Ye, N., & Li, X. (2001). A machine learning algorithm based on supervised clustering and classification. In Active Media Technology (pp. 327-334). Springer Berlin Heidelberg.