论文信息 - Semantic session analysis for Web usage mining

Semantic session analysis for Web usage mining

A semantic session analysis method partitioning Web usage logs is presented. Semantic Web usage log preparation model enhances usage logs with semantic. The Markov chain model based on ontology semantic measurement is used to identifying which active session a request should belong to. The competitive method is applied to determine the end of the sessions. Compared with other algorithms, more successful sessions are additionally detected by semantic outlier analysis.

Zhang Hui | Song Han-tao | Xu Xiaomei

[1] Dale Schuurmans,et al. Session Boundary Detection for Association Rule Learning Using n-Gram Language Models , 2003, Canadian Conference on AI.

[2] Hui Zhang,et al. Fuzzy Related Classification Approach Based on Semantic Measurement for Web Document , 2006, Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06).

[3] Tom Heskes,et al. Categorization of web pages and user clustering with mixtures of hidden Markov models , 2008, KDD 2008.

[4] Dino Pedreschi,et al. Web log data warehousing and mining for intelligent web caching , 2001, Data Knowl. Eng..

[5] Hui Zhang,et al. Construction of Ontology-Based User Model for Web Personalization , 2007, User Modeling.

[6] James E. Pitkow,et al. In Search of Reliable Usage Data on the WWW , 1997, Comput. Networks.

[7] Ramesh R. Sarukkai,et al. Link prediction and path analysis using Markov chains , 2000, Comput. Networks.

[8] Jun Hong,et al. Using Markov models for web site link prediction , 2002, HYPERTEXT '02.

[9] Myra Spiliopoulou,et al. A Framework for the Evaluation of Session Reconstruction Heuristics in Web-Usage Analysis , 2003, INFORMS J. Comput..