Improving multi-class co-clustering-based collaborative recommendation using item tags

Abstract

Multi-class Co-Clustering (MCoC)-based recommendation system is a method for recommending favorite items to users. It, firstly, groups items and users in a way that users have common interests and their favored items are put in the same group. Then, to estimate unrated items of each group, for each group, an independent collaborative filtering approach is implemented. MCoC-based recommendation system uses rating vectors to determine similar items and to group them together. We expect that the ratings of two items with the same tag be closer than two items with different tags. Therefore, tags can also be used to determine similar items for co-clustering. The purpose of this study is to enhance the performance of co-clustering to increase the accuracy of MCoC-based recommendation system by using item tags in addition to item rating vectors. Our experiments show that mean absolute error of our proposed method is much less than that of MCoC-based recommendation system.