Personalized Recommendation of Classification based on Social Relationship and Time Information
- 10.2991/icmmita-16.2016.188How to use a DOI?
- Recommender performance; Social relationship; Time information; Classification
Improving recommender performance is beneficial. However, sparsity and scalability of data is a problem faced by recent recommender systems. Customer interests and available products are changing constantly. Social interactions among users are highly influential on the effectiveness of the recommendation. Following these intuitions, this paper proposed a recommendation method incorporating with social and temporal information with probabilistic matrix factorization, which is called PMFST (Probabilistic Matrix Factorization with Social and Temporal information), to solve the problem of data sparsity and achieve real and dynamic recommender performance. The experiment on two real data sets shows that the proposed method outperforms the state-of-the-art methods in terms of minimal error and recommender performance.
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Mengzi Tang AU - Li Li PY - 2017/01 DA - 2017/01 TI - Personalized Recommendation of Classification based on Social Relationship and Time Information BT - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications PB - Atlantis Press SN - 2352-538X UR - https://doi.org/10.2991/icmmita-16.2016.188 DO - 10.2991/icmmita-16.2016.188 ID - Tang2017/01 ER -