Abstract | ||
---|---|---|
Due to the data sparsity problem, social network information is often used to improve the performance of recommendation system. Social recommendation is one of recommendation systems, which has gradually become the hot research field of recommendation because it can better simulate the recommendation process in the real world and better reflect the role of people in the process of recommendation. However, most of the existing methods of social recommendation ignore the impact of the item's contextual information, and only consider the connection between users. In order to take full advantage of contextual information and social relationships into consideration, this paper proposes a novel social recommendation method, named SocialConvMF, which integrates trust relationship and Convolutional Neural Network (CNN) into Probability Matrix Factorization (PMF). First, it uses the trust-aware social recommendation method; then captures contextual information in the document; finally, it utilizes trust-aware and contextual information to do social recommendation. Experimental results on three real-world datasets demonstrate that our proposed method can further improve the accuracy of the rating forecast in social recommendation. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICCNC.2019.8685666 | 2019 International Conference on Computing, Networking and Communications (ICNC) |
Keywords | Field | DocType |
data sparsity,trust relationship,convolutional neural network,CNN,probability matrix factorization,PMF,recommendation system,social network information,document context-aware social recommendation method,trust-aware social recommendation method,social relationships,contextual information | Recommender system,Contextual information,Social relationship,Trust relationship,Social network,Information retrieval,Convolutional neural network,Computer science | Conference |
ISSN | ISBN | Citations |
2325-2626 | 978-1-5386-9224-0 | 0 |
PageRank | References | Authors |
0.34 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guangxia Xu | 1 | 42 | 9.46 |
Lijie He | 2 | 0 | 0.34 |
Mengxiao Hu | 3 | 0 | 1.69 |