Consideration about Applicability of Recommender System Employing Personal-Value-Based User Model

This paper presents consideration about applicability of recommender system based on personal-value-based user model. Existing methods such as collaborative and content-based approaches tend to be less-accurate for new users and items owing to the lack of the relation between items and users´ preference. While existing recommender systems usually employ user preference of items to make recommendations, proposed method focuses on users´ personal values, which mean value judgments regarding on which attributes users put a high priority. Proposed recommender system employing personal-value-based user model is therefore expected to realize more precise recommendation in cold-start situations. Moreover, the tendency of personal values could be categorized into several types, which would affect the ratings for recommended items. This paper shows experimental results of recommendation for several user types, based on which relation between user type and recommendation is discussed.