Deriving a Categorical Vector Space Model for Web Page Recommendations Based on Wikipedia’s Content

摘要

This work models web pages and users for web pagernrecommendation by deriving a categorical vector spacernmodel (WikiVSM). We augment Wikipedia’srncategorization system with keywords extracted fromrnWikipedia’ pages. By applying keyword matching, any webrnpage can be mapped into WikiVSM. We comparernWikiVSM’s performance with Vector Space Model (VSM)rnregarding recommending topically relevant web pages tornindividual users based on their browsing history. Resultsrnindicate that WikiVSM performs significantly better inrngenerating recommendations. This is possibly due tornfeatures of Wikipedia and our augmentation.