Semantically Enriched Recommender Engine: A Novel Collaborative Filtering Approach Using "User-to-User Fast Xor Bit Operation"

In this paper, we focus on Collaborative Filtering to provide recommendations to users that fit their profiles. We employed two methods: (1) K-Nearest Neighbors classifier, and (2) a fast implementation of Collaborative Filtering approach: “user-to-user fast XOR bit operation”. Both techniques serve the same objective, which is modifying the user´s ontology profile (semantic profile). Technically, Collaborative Filtering extends the user´s ontology profile based on the interests of a community of similar users. Also, we describe the implementation of the recommender system on a real platform, known as Hyper Many Media at Western Kentucky University. Finally, we evaluate the system based on Top-n-Recall and Top-n-Precision. The results show an improvement in Recall and Precision using Collaborative Filtering.