GMAT:A Graph Modeling Method for Group Preference Prediction

Preference prediction is the building block of personalized services,and its implementation at the group level helps enterprises identify their target customers effectively.Existing methods for preference prediction mainly focus on behavioral interactions to extract the associations between groups and products,ignoring the importance of other auxiliary records(e.g.,online reviews and social tags)in association detection.This paper proposes a novel method named GMAT for group preference prediction,aiming to collectively detect the sophisticated association patterns from user generated content(UGC)and behavioral interactions.In doing so,we construct a tripartite graph to collaborate these two types of data,and design a deep-learning algorithm with mutual attention module for generating the contextualized representations of groups and products.Extensive experiments on two real-world datasets show that GMAT is superior to other baselines in terms of group preference prediction.Additionally,GMAT is able to improve prediction accuracy compared with its different variants,further verifying the proposed method’s effectiveness on association pattern detection.

Users Intention for Continuous Usage of Mobile News Apps:the Roles of Quality,Switching Costs,and Personalization

Mobile news apps have emerged as a significant means for learning about latest news and trends. However, in light of numerous news apps and information overload, motivating users to adopt one app is a major concern for both the industry and academia. Therefore, considering the attributes of mobile news and the debate on switching costs in the Internet context, based on the expectation-confirmation model (ECM), this study suggests that switching costs still exist and have a significant moderating effect on user satisfaction and continuous usage of mobile news apps. Furthermore, the different influences of information quality, system quality and service quality on continuance intention, user satisfaction and switching costs are discussed, showing that quality of information has a significant impact on users’ continuous usage of mobile news apps through increasing perceived usefulness, whereas personalized service quality have stronger effects through increasing user satisfaction and switching costs.

Assimilation and Contrast:The Two-sided Anchoring Effects of Recommender Systems

Previous studies on the behavioral implications of recommender systems suggest that consumer preferences after consumption are malleable and tend to shift towards the ratings presented by a recommender system because of the anchoring effects.Drawing upon the literature on consumer satisfaction,we show that such a view on the anchoring effects of recommender systems is incomplete.Apart from the assimilation effects that pull the consumers’preferences towards the anchor,the contrast effects may shift their preferences in the other direction.Therefore,we theoretically hypothesize that the impacts of recommendations on consumers’constructed preferences are dependent on the level of deviation of the presented rating.The hypotheses are validated through a laboratory experiment.Our findings extend the existing literature on behavioral implications of recommender systems and provide a more comprehensive theoretical lens for understanding the anchoring effects,which may offer helpful insights for improving the design and use of recommender systems.