Modern society has now grown accustomed to reading online or digital news. However, the huge corpus of information available online poses a challenge to users when trying to find relevant articles. A hybrid system "Personalized News Recommender Using Twitter' has been developed to recommend articles to a user based on the popularity of the articles and also the profile of the user. The hybrid system is a fusion of a collaborative recommender system developed using tweets from the "Twitter" public timeline and a content recommender system based the user's past interests summarized in their conceptual user profile. In previous work, a user's profile was built manually by asking the user to explicitly rate his/her interest in a category by entering a score for the corresponding category. This is not a reliable approach as the user may not be able to accurately specify their interest for a category with a number. In this work, an automatic profile builder was developed that uses an implicit approach to build the user's profile. The specificity of the user profile was also increased to incorporate fifteen categories versus seven in the previous system. We concluded with an experiment to study the impact of automatic profile builder and the increased set of categories on the accuracy of the hybrid news recommender system.
展开▼
