Discriminate2Rec: Negation-based dynamic discriminative interest-based preference learning for semantics-aware content-based recommendation

Content-based recommender systems (CBRSs) have shown to be highly effective for enhancing user experience in various problems and application domains. Most existing CBRSs employ static preference learning techniques, neglecting that user preferences constantly change over time and are attributed to only a set of certain attributes at a certain period of time due to the existence of temporal dynamics, as only certain attributes of highly preferred items actually reflect user positive interests, while many others might have neutral or even negative influence on user preferences regardless their semantic similarity. Lacking the efficiency in handling these problems poses semantical and temporal incoherence in user profiles, which significantly affects the recommendation accuracy. This paper presents Discriminate2Rec, a three-stage preference learning model that discriminates between items' attributes based on their influence on user temporal preferences to improve temporal and semantical attribute-level profile coherence for more accurate recommendation. Evaluation is made on three real-world data sets. The results demonstrate the effectiveness of Discriminate2Rec in outperforming state-of-the-art approaches in terms of recommendation accuracy. More in detail, the results also demonstrate that: (1) learning user profiles based on the discrimination between items' attributes improves the attribute-level profile coherence; (2) modelling the negation in user temporal preferences allows Discriminate2Rec to recommend items whose content are semantically similar to user positive interests to which user negative interests are semantically irrelevant; (3) this novel combination significantly improves temporal and semantical attributelevel profile coherence, and maximises the utilisation of signal, thus significantly improves the recommendation accuracy consistently over time.

Automated summary

This paper presents a preference learning model called Discriminate2Rec, which improves the recommendation accuracy of content-based recommender systems by enhancing the coherence of user profile at the semantic and temporal attribute level. Evaluation on three real-world datasets demonstrates the superior performance of Discriminate2Rec compared to state-of-the-art approaches.