Educational Group Recommendations with Virtual Leaders

Recommender systems have been applied in the area of education to suggest learning materials, assist informal learning, recommend projects or advisors, and so forth. In the process of teaching or learning, students may work together in a group. In this case, the group recommendations may come into play. In this paper, we propose to build a novel group recommendation model for education by introducing a virtual leader to each group. More specifically, we represent these virtual leaders by the personality traits, and learn these representations towards the optimization of the recommendations. Our experimental results demonstrate the effectiveness of the proposed models in comparison with other group recommendation models.