Abstract
This paper improves Collaborative Filtering Algorithms (CF) to recommend similar bookmarks for users of Social Bookmark Services. Standard CF algorithms have a problem with precision in multi-genre cases such as social bookmarks. We aim at solving this issue and propose a personal classification space-based collaborative filtering algorithm. Our interpretation is that users' bookmarks are disposed in their own classification space made by tags. The bookmark is transformed into a scalar as a similarity to a starting bookmark for a recommendation. We compare the personal classification space with others' space using the similarities. We handle the similarities as the rating to the bookmark in standard CF algorithms. The proposed algorithm is compared with other existing algorithms. In conclusion, our algorithm shows better precision than others.
