A Graph Indexing Approach for Content-Based Recommendation System

Conventional content-based recommendation systems use different classifying algorithms to group items into several groups and for each group generate a ranking list of items. An important characteristic of conventional content-based recommendation systems is that they use the same ranking list to make recommendations for items in each group, ignoring differences among items inside of a group. The paper proposes a content-based recommendation system built on top of a weighted un-directional graph. The graph describes the content similarity between items based on the semantic relations of their metadata. Neighbors of a node in the graph construct a ranking list of items to be recommended and there is a ranking list for each item. So it is able to emphasize differences among related items. We developed a prototype of the proposed system in Kaleido Photo project, and it proves to be sufficient to recommend most similar photos according to what the user is viewing.