Multi-modal matrix factorization with side information for recommending massive open online courses

Abstract

Massive open online courses (MOOCs) have recently gained a huge users’ attention on the Web. They are considered as a highly promising form of teaching from leading universities such as Stanford and Berkeley. However, users confront the problem of choosing among thousands of offered MOOCs. In such a scenario of severe “information overload”, recommender systems can be very useful to recommend the right course to a user, since they base their operation on past user’s log history. For example, Coursera recommends courses to users so that, they can acquire those skills, that are expected from their ideal job. These user’s preferences are not expected to be independent from others choices, as users follow trends of similar behaviour. In this paper, we propose, xSVD++, where the “x” means that it is a multi-dimensional Matrix Factorization (MMF) model combined with Collaborative Filtering (CF) algorithm, which exploits information from external resources (i.e., users’ skills, courses’ characteristics, etc.) to predict course trends and to perform rating predictions according to them. Our experimental results indicate that xSVD++ is superior over classic and non-negative matrix factorization algorithms and the state-of-the-art CMF, and SVD++ algorithms.