User and Item Modeling Methods Using Customer Reviews towards Recommender System Based on Personal Values

This paper proposes user and item modeling methods towards recommender systems based on personal values. Marketing fields have been taking notice of personal values, because that such values are significantly related to user 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 that show what attributes users put a high priority. The influence of each attribute on item evaluation is determined based on correspondence between ratings for item and the attribute. The proposed method is applied to actual review data, of which results supports the assumption that different users put high priorities on different attributes.