A Framework for Modeling, Computing and Presenting Time-Aware Recommendations

Lately, recommendation systems have received significant attention. Most existing approaches though, recommend items of potential interest to users by completely ignoring the temporal aspects of ratings. In this paper, we argue that time-aware recommendations need to be pushed in the foreground. We introduce an extensive model for time-aware recommendations from two perspectives. From a fresh-based perspective, we propose using different aging schemes for decreasing the effect of historical ratings and increasing the influence of fresh and novel ratings. From a context-based perspective, we focus on providing different suggestions under different temporal specifications. To facilitate user browsing, we propose an effective presentation layer for time-aware recommendations based on user preferences and summaries for the suggested items. Our experiments with real movies ratings show that time plays an important role in the recommendation process.