A novel scheme for movie recommendation system using user similarity and opinion mining

Abstract

Movie recommender system has become an interesting research topic due to the growth of users in a mobile environment. To recommend movies, a complete aggregation of user’s preferences, feelings (emotions), and reviews required to assist users for find best movies in more convenient way. However to deal with the recommendation system, we must consider timeliness and accuracy. In this paper, we propose a movie recommender system based on new user similarity metric and opinion mining. The primary objective of this paper is to find the type of opinions (positive, negative or neutral) for movies and also suggest top-k recommendation list for users. We extract aspect-based specific ratings from reviews and also recommend reviews to users depends on user similarity and their rating patterns. Finally, validating the proposed movie recommendation system for various evaluation criteria, and also the proposed system shows better result than conventional systems.