Emotion Distribution Profile for Movies Recommender Systems

Reviews, comments and feedbacks are user-generated content which comprises of insights regarding a given item or a thing and furthermore user’ emotions. Various highlights of user-created content incorporate feelings, opinions and survey helpfulness that shows a promising research in the field of recommender systems. Reviews contain various words and sentences that show their natural passionate substance. Emotions are a significant component of human conduct. They enable us for decision making by generating a liking or disliking toward a particular item. This paper harnesses reviews as the content generated from user to exploit, emotion as a basis for generating recommendations. Through experiments conducted on real dataset, our proposed approach compares the performance with traditional item-based collaborative filtering approach. Experimental results show 173% increase in prediction accuracy for top 25 recommendations as compared to prediction accuracy based on rating-based item similarity.