Emotion-based music recommendation by association discovery from film music
Proceedings of the 13th annual ACM international conference on Multimedia
Insert movie reference here: a system to bridge conversation and item-oriented web sites
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Google news personalization: scalable online collaborative filtering
Proceedings of the 16th international conference on World Wide Web
| Hi-index | 0.00 |
Many online movie sites or music sites offering recommendation services employ a collaborative filtering technique archived by analyzing customers' satisfaction rating, evaluation, search history, download records etc. This approach, however, has difficulty with reflecting individuals' perosonalities and their own taste for the recommendation. Exploiting such emotional data to a film recommendation remains a challenge in the present. To solve this, we propose an emotion words selection method usable for the collaborative filtering. Through the proposed emotion-based collaborative filtering method, a recommendation system can exploit individuals' emotional differences on the movie items for the recommendation process. This approach was proven by gathering users' emotion words selection and satisfaction rating data on several films, and comparing them with MBTI (Myers-Briggs Type Indicator) that is a representative psychometric test for measuring psychological preferences and personalities. This study assumes that individual's movie taste is much related to the personalities classifiable by MBTI types, because movie taste and evaluation on a movie is influenced by individual's subjective matters. The results of this study show that emotion words based collaborative filtering method is appropriate for extracting users' MBTI types. Thus, if a recommendation service offers users films based on their MBTI types, the users can be recommended more customized films.