Sentiment-Based Model for Recommender Systems

Abstract

Recommender systems have proven to be a valuable way for online users to cope with the issues of information overload. They have become one of the most powerful and popular tools in electronic commerce as illustrated by Amazon.com, YouTube, Netflix, Yahoo, and IMDb. While recommender systems have shown significant contribution, they still suffer from the long-standing problems related to cold-start users and data-sparsity. This is due to the fact that recommendation algorithms mostly rely on users' rating to make prediction of items. Such ratings are usually insufficient and very limited. On the other hand, sentiment ratings of items which can be derived from online news services, blogs, social media or even from the recommender systems themselves are seen capable of providing better recommendations to user as opposed to tags alone. Sentiment-based model has been exploited in recommender systems to overcome the data-sparsity problem that exists in conventional recommender systems. Hence, embedding sentiment in recommender systems may significantly enhance the recommendation quality of recommender systems. Among the aims of this research is to integrate sentiment analysis in recommender systems particular to those items with no associated rating that commonly contribute to the problem of data-sparsity.