Evaluating Diversification in Group Recommender Systems

Abstract

The formation of groups is an ordinary event in our routines. For example, people used to lunch, travel, or hang out in groups. Conversely, getting a consensus over an item may be difficult for some groups as the number of digital information increases. Group Recommender Systems (GRS) rise to assist in this task, as they filter which items may be more relevant to the group. Although there are consensus techniques to help in this matter, recommendations to groups can become monotonous, and this opens space for applying diversification techniques to improve recommendations. In this paper, we expose a model for recommendation to groups using diversification techniques and present the results of the online experiment where the proposal obtained an increase in precision at all levels compared with baseline.