Implicit Acquisition of User Personality for Augmenting Recommender Systems

In recent years, user personality has been increasingly recognized as a valuable resource being incorporated into the process of generating recommendations. However, the effort of explicitly acquiring users' personality traits via psychological questionnaire is unavoidably high, which may impede the application of personality-based recommenders in real life. My PhD research aims to investigate how to derive users' personality from their implicit behavior and further improve the existing recommender systems. For this purpose, we first identify significant features through experimental validation. We then build inference model to unify these features for determining users' Big-Five personality traits. We further develop personalized recommender systems by incorporating the inferred personality. Our study would indicate an effective solution to boost the applicability of personality-based recommender systems in the online environment.