Relation-aware Graph Convolutional Networks for Library Book Recommendation
- DOI
- 10.2991/978-2-38476-158-6_12How to use a DOI?
- Keywords
- Graph Convolutional Networks; Relational Attentive; Book Recommendation; Library
- Abstract
In response to the issues of sparse borrowing relationship data, shifting content interests, and recommendation cold start in university library, this paper proposes a personalized book recommendation method based on Graph Convolutional Networks (GCNs). This method possesses conventional prediction and inductive capabilities by constructing a global tripartite graph of borrowers, books, and subjects and training a relation-aware GCN on local subgraphs. Additionally, a temporal self-attention (TSA) mechanism is proposed to encode long-term and short-term temporal patterns of borrower preferences, overcoming the variations and decay of interests over time. Experimental results conducted on two datasets demonstrate the advanced performance of our method, which is further validated through testing with real library data. Our proposed method effectively addresses the recommendation cold start problem, and places greater emphasis on the recent borrowing interests of readers, thereby improving the accuracy of recommendations.
- Copyright
- © 2023 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Shuaishuai Fan AU - Weiming Li PY - 2023 DA - 2023/12/18 TI - Relation-aware Graph Convolutional Networks for Library Book Recommendation BT - Proceedings of the 2023 International Conference on Applied Psychology and Modern Education (ICAPME 2023) PB - Atlantis Press SP - 79 EP - 86 SN - 2352-5398 UR - https://doi.org/10.2991/978-2-38476-158-6_12 DO - 10.2991/978-2-38476-158-6_12 ID - Fan2023 ER -