recommender system nowadays is used to deliver services and information to users. A recommender system is suffering from problems of data sparsity and cold start because of insufficient user rating or absence of data about users or items. This research proposed a sentiment analysis system work on user reviews as an additional source of information to tackle data sparsity problems. Sentiment analysis system implemented using NLP techniques with machine learning to predict user rating form his review; this model is evaluated using Yelp restaurant data set, IMDB reviews data set, and Arabic qaym.com restaurant reviews data set under various classification model, the system was efficient in predicting rating from reviews.

The expansion of web applications like e-commerce and other services yields an exponential increase in offers and choices in the web. From these needs, the recommender system applications have arisen. This research proposed a recommender system that uses user's reviews as implicit feedback to extract user preferences from their reviews to enhance personalization in addition to the explicit ratings. Diversity also improved by using k-furthest neighbor algorithm upon user's clusters. The system tested using Douban movie standard dataset from Kaggle, and show good performance.