A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Abstract

Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to cope with changes of user's preferences. This paper summarizes a research that is still going on, to solve the lack of novelty, serendipity and dynamism in recommender systems. Recent research has demonstrated different methodologies to create recommender systems , unfortunately many of these which were evaluated using user-centric evaluation frameworks fall short to fulfill users' satisfaction. Therefore we propose a unique computational method to create a novel, serendipitous and dynamic recommender system. We used web content mining to gather user profiles from social media, model these profiles, and create an algorithm to suggest user preferences. The results testify that many users' social profiles for Zimbabweans dominate quite well to determine user preferences. Therefore recommender developers for developing countries, has to gather user's social profiles to predict their preferences. The main contribution is a holistic approach to model and predict dynamic user-specific preferences from categorized social media profiles namely: social, psychological, cultural, and economic profiles