Existing recommendation systems mainly focus on achieving high accuracy, and ignore the psychological motivation behind human exploration. Inspired by the theory of curiosity, several curiosity-driven recommendation methods have been proposed. Despite the impressive success, these methods still suffer from two major limitations. One is that curiosity is only used to reorder the generated recommendation lists while ignoring its crucial role in the entire user decision-making process. Another is to evaluate conflict stimuli solely based on social friends factor, neglecting individual preference factor. In these regards, we propose a novel Preference-Consensus-Conflict Curiosity (P3C) method. As its core, a dual-branch network based on individual preference and social consensus is designed to model users’ conflict-driven curiosity. Furthermore, a re-weighting strategy combined with the curiosity is adopted for model training. Benefit from this, P3C can provide each user with a candidate item list that match their curiosity level. Extensive experiments conducted on MovieLens-1M and LastFM-2K demonstrate that P3C outperforms all the other competitors in diversity metrics (Coverage and Novelty), and achieves satisfactory performance in accuracy metrics (Precision, Recall, and NDCG). The code is available at https://github.com/Run542968/P3C.
Ranking items to users is a typical recommendation task, which evaluates users’ preferences for certain items over others. Easy access to social networks has motivated researchers to incorporating trust information for recommendation. In this paper, aiming at offering fundamental support to the trust-based research for item recommendation, we conduct an in-depth analysis on Epinions, Ciao, and FilmTrust data sets. We find that a user’s selection of an item is influenced not only by her trustees but also by her trusters. We leverage this “dual roles influence” to derive two more accurate matrix factorization (MF)-based ranking models, namely, BPRDR and FSDR , respectively. In more detail, the first BPRDR model performs three pairwise preferences comparisons under the Bayesian personal ranking framework, considering the dual roles influence in its ranking assumptions. The second FSDR is an improved factored similarity model as it incorporates dual roles influence to contribute its ranking scores. Extensive experiments on three data sets show that it is essential to consider the dual roles influence when generating top- $K$ item recommendation.
Distrust based recommender systems have drawn much more attention and became widely acceptable in recent years. Previous works have investigated using trust information to establish better models for rating prediction, but there is a lack of methods using distrust relations to derive more accurate ranking-based models. In this article, we develop a novel model, named TNDBPR (Trust Neutral Distrust Bayesian Personalized Ranking), which simultaneously leverages trust, distrust, and neutral relations for item ranking. The experimental results on Epinions dataset suggest that TNDBPR by leveraging trust and distrust relations can substantially increase various performance evaluations including score, , , , and .
18 May 2021 in Proceedings of the AAAI Conference on Artificial Intelligence
Curiosity affects users' selections of items, and it motivates them to explore the items regardless of their interests. This phenomenon is particularly common in social networks. However, the existing social-based recommendation methods neglect such feature in social network, and it may cause the accuracy decease in recommendation. What's more, only focusing on simulating the users' preferences can lead to information cocoons. In order to tackle the problem, we propose a novel Curiosity Enhanced Bayesian Personalized Ranking (CBPR) model. Our model makes full use of the theories of psychology to model the users' curiosity aroused when facing different opinions. The experimental results on two public datasets demonstrate the advantages of our CBPR model over the existing models.