Individual Interest and Trust Driving Collective Intelligence Awareness for Social Recommendation

Lin Cui, Caiyin Wang, Jia Wu, Jian Yang, Michael ShengIJCNN 2018 · OpenReview

Abstract

Social recommendation incorporates the social information of the user, such as friend relationship and trust relationship into the traditional recommendation system. From this point of view, social recommendation expands the function of the traditional recommendation to some extent. However, the existing social recommendation methods mostly focus on the general social relation between users and neglects the refinement of group information based on individual interest and trust. To this end, this paper proposes a novel social recommendation model based on the collective intelligence awareness driven by individual interest and trust. Experiments on two real-world datasets demonstrate that the proposed social recommendation method based on group information and individual feature outperforms the three baseline methods on the two evaluation metrics MAE and RMSE.
BibTeX
@inproceedings{cui2018individual,
  author = {Lin Cui and Caiyin Wang and Jia Wu and Jian Yang and Michael Sheng},
  title = {{Individual Interest and Trust Driving Collective Intelligence Awareness for Social Recommendation}},
  booktitle = {IJCNN},
  year = {2018},
  url = {https://openreview.net/forum?id=1LiL6hnMmb},
}

Loading related content...

Figure