An Black-Box Testing Approach on User Modeling in Practical Movie Recommendation Systems
Since there have been many practical recommendation services in real world, main research questions are i) how such services provide users with recommendations, and ii) how they are different from each other. The aim of this paper is to evaluate user modeling process in several practical recommendation systems. Black-box testing scheme has been applied by comparing recommendation results. User models (i.e., a set of user ratings) have been synthesized to discriminate the recommendation results. Particularly, we focus on investigating whether the services consider attribute selection.
KeywordsRecommendation systems Personalization User modeling Black-box testing Comparative study
Unable to display preview. Download preview PDF.