摘要
In this paper a web user's surfing behavior is represented as a web access pattern. Then we adopt a fuzzy rough c-means method to cluster these web access patterns into groups. Each group includes patterns disclosing same or similar surfing behaviors. And an optimized algorithm is employed to gain the better clustering results. Finally, we have performed an evaluation of the proposed approach with an example and an experiment. We have found that the proposed algorithm is feasible and effective.
延伸閱讀
- 周世寧（2005）。Data Clustering based on Results of Association Rules:with Analysis of Web Browsing Patterns Application〔碩士論文，淡江大學〕。華藝線上圖書館。https://doi.org/10.6846/TKU.2005.00157
- 黃威穎（2006）。Hierarchically Dynamic Clustering of Web Search Results〔碩士論文，元智大學〕。華藝線上圖書館。https://doi.org/10.6838/YZU.2006.00124
- 洪秉儒（2011）。Web Text Clustering with Dynamic Theme〔碩士論文，國立中央大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0031-1903201314411137
- 卜小蝶、陳思穎（2007）。User Evaluation of Web Clustering Search Engines。圖書資訊學研究，2(1)，55-80。https://www.airitilibrary.com/Article/Detail?DocID=19909128-200712-2-1-55-80-a
- Hassan, M. T., & Karim, A. (2011). Impact of Behavior Clustering on Web Surfer Behavior Prediction. Journal of Information Science and Engineering, 27(6), 1855-1870. https://doi.org/10.6688/JISE.2011.27.6.4