Arabic Text Documents Recommendation Using Joint Deep Representations Learning

Abstract Although a huge amount of data has been provided on the web to meet different needs of users, it has been more difficult to quickly make satisfactory choices. Therefore, recommender systems have been introduced for offering relevant data and providing users with personalized recommendations. Traditional collaborative based methods modelled efficiently users and items from their rating patterns. By cons, they suffered from the data sparsity problem. As a solution, text user-generated data (e.g., reviews) were useful to provide rich semantic information of user preferences and item features. Seeing that opinions and ratings were complementary, we proposed to fuse them and learn more accurate representations of users and items for recommendation. Unlike Arabic which has received less attention, the majority of methods offered have been focused on English language. It has been represented a fundamental issue in Natural Language Processing (NLP) and artificial intelligence. In this paper, a neural collaborative embedding- and filtering-based approach was proposed for Arabic textual documents recommendation. Due to the recent advances on neural networks, our idea was to couple deep features learning- and deep interaction modelling- based encoders. Indeed, two branches of recurrent neural networks were combined to extract latent features of users and items. Using the generated representations as inputs, deep user-item interactions were captured by stacking multiple layers. This method has proved its efficiency to simultaneously capture the global context and the word frequency information, learn thereafter the obtained high-level latent features and produce final ratings. Extensive experiments on a standard Arabic dataset showed the superiority of our model than state-of-the art methods.