Résumé
•Scrutiny of the current state of the art in context-aware recommender systems by classifying and studying the distribution of the reviewed research works.•Thorough literature review of papers published between 2000 and 2016 on context-aware recommender system area.•Definition of the contextual factors used to make recommendations.•Identification of the methods employed to measure the relevance of contextual information in order to define an exhaustive contextual model.•Determination of the techniques used for adopting contextual information to make recommendations.•Identification of the solutions proposed to solve the cold start problem.•Discussion of the selection of datasets and the type of experiments used for evaluation.
Recommender systems have recently been singled out as a fascinating area of research, owing to the technological progress in mobile devices, such as smartphones and tablets, as well as to the rapid growth of social networking. In this respect, the main purpose of recommender systems is to suggest items that help users to make decisions from a large number of possible actions such as what place to visit, what movie to watch, or which friend to add to a social network system. In mobile environment, many personal, social and environmental contextual factors can be integrated into the recommendation process in order to provide the correct recommendation to a special user, at the perfect moment, in the appropriate location based on his/her emotional state, his/her current activity and past behavior. This paper provides an overview of context-aware recommender systems in mobile environment. The objective of this systematic review is to investigate the current state of the art in context-aware recommender systems and classify the reviewed research papers. This study aims equally to identify the possible future directions in this research area.