Paper Title
Keyword Based User Profiling for News Recommendation

News Recommendation is increasingly being deployed by online news publishers. Recommender Systems are used as a way to deal with information overload and to increase page views. Collaborative filtering and content based filtering are two common approaches used in recommendation systems. In this paper, we propose a News Recommendation System Model that uses keywords obtained from the articles to profile the user. We then use a collaborative filtering model to generate recommendations to the users. Coping with ever changing user interests is also a major challenge for recommendation system. This model also proposes a decay function to deal with such a challenge. Index Terms— Recommender Systems, Time Based, Keywords, Collaborative Filtering, Matrix Factorization