Design and User Perception Issues for Personality-Engaged Recommender Systems

Recommender systems have emerged, as an intelligent information filtering tool, to help users effectively identify information items of interest from a set of overwhelming choices and provide personalized services. Most recommendation technologies typically rely on ratings or item attributes to generate recommendations. Studies show that personality influences people's decision making processes and interests. However, little research has ventured into the area of incorporating personality into recommender systems. The utilization of personality characteristics in recommender systems and the exploration of user perceptions of personality-engaged recommendation technologies are the two main concerns of this thesis. In all of our studies, the five factor model (FFM), one of the most widely employed personality models, was adopted to establish user personality profiles. Firstly, we have aimed at designing effective personality-engaged recommender systems, with the emphasis on how to integrate personality into the recommendation generation framework, and how to utilize personality information to address the problems that exist in current recommender systems. We implemented a personality-based music recommender system prototype based on the findings from prior psychological studies. This system builds user personality profiles by means of personality quizzes, and it accordingly predicts their musical preferences and makes music recommendations. This system prototype was employed in our later user study investigating user perceptions of this novel recommendation technology. Moreover, we investigated how to incorporate personality into collaborative filtering recommender systems with the purpose of alleviating new user and dataset sparsity problems. In contrast to the traditional rating-based collaborative filtering method, the proposed three variants which take personality characteristics into account significantly improve the prediction accuracy in both cold-start scenarios (i.e., new user & dataset sparsity). Furthermore, in order to generalize the personality-engaged recommendation technology to other item domains, we used matrix factorization methods to automatically discover the links between personality traits and items. Consequently, recommendations were generated based on the discovered relationships. The empirical results show that the proposed methods achieve superior performances compared to other tested methods. In particular, the proposed method can produce highly accurate recommendations, even though no rating is available. It has been demonstrated that the proposed method can be applied to design effective gift recommender systems where rating information is hard to obtain. Secondly, we have conducted two user studies with the aim of investigating user perceptions of personality-engaged recommender systems. One compares a personality-quiz based movie recommender system with a baseline rating-based recommender system, and identifies the fa