The Community for Technology Leaders
2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI) (2016)
Omaha, NE, USA
Oct. 13, 2016 to Oct. 16, 2016
ISBN: 978-1-5090-4470-2
pp: 240-247
ABSTRACT
With the prevalence of social networks, social recommendation is rapidly gaining popularity. Currently, social information has mainly been utilized for enhancing rating prediction accuracy, which may not be enough to satisfy user needs. Items with high prediction accuracy tend to be the ones that users are familiar with and may not interest them to explore. In this paper, we take a psychologically inspired view to recommend items that will interest users based on the theory of social curiosity and study its impact on important dimensions of recommender systems. We propose a social curiosity inspired recommendation model which combines both user preferences and user curiosity. The proposed recommendation model is evaluated using large scale real world datasets and the experimental results demonstrate that the inclusion of social curiosity significantly improves recommendation precision, coverage and diversity.
INDEX TERMS
Recommender systems, Motion pictures, Predictive models, Cultural differences, Social network services, Psychology, Context
CITATION

Q. Wu, S. Liu, C. Miao, Y. Liu and C. Leung, "A Social Curiosity Inspired Recommendation Model to Improve Precision, Coverage and Diversity," 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI), Omaha, NE, USA, 2016, pp. 240-247.
doi:10.1109/WI.2016.0042
89 ms
(Ver 3.3 (11022016))