Proceedings of the 3rd International Conference on Digital Economy and Computer Application (DECA 2023)

Research on Personalized News Recommendation Model Based on Knowledge Graph

Authors
Suicheng Li1, Xiaotian Wang1, *, Shaoyang Zhang1, Jiabin Wei1, Yanying Shang1
1School of Economics and Management, Xi’an University of Technology, Xi’an, China
*Corresponding author. Email: 496996232@qq.com
Corresponding Author
Xiaotian Wang
Available Online 4 December 2023.
DOI
10.2991/978-94-6463-304-7_35How to use a DOI?
Keywords
News recommendations; Knowledge graph; Deep learning; Theme model
Abstract

By constructing a personalized news recommendation model based on a knowledge graph, the problem of ignoring knowledge correlation in multi-class text information methods has been effectively solved. The study analyzed the characteristics of news texts, treating titles and abstracts as key information components, and using word vectors and knowledge graph feature learning methods for vectorization processing. In terms of model construction, sub-modules such as multi-perspective news features, user click behaviorand click probability prediction were introduced. Through techniques such as convolutional neural networks and attention mechanisms, multi-dimensional information of news was comprehensively considered, achieving more accurate personalized recommendations. The experimental results show that the knowledge graph-based model performs well in AUC, MRR nDCG@5 nDCG@10,Compared to the benchmark model, the evaluation indicators have increased by 3%, 2.6%, 2.5%, and 3%. The ablation experiment has demonstrated the positive effects of knowledge graphs, multi-perspective news features, and attention mechanisms. This study provides new ideas for knowledge graph-based news recommendations, which helps to improve user satisfaction and strengthen the platform’s service capabilities.

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.

Download article (PDF)

Volume Title
Proceedings of the 3rd International Conference on Digital Economy and Computer Application (DECA 2023)
Series
Atlantis Highlights in Computer Sciences
Publication Date
4 December 2023
ISBN
10.2991/978-94-6463-304-7_35
ISSN
2589-4900
DOI
10.2991/978-94-6463-304-7_35How to use a DOI?
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  - Suicheng Li
AU  - Xiaotian Wang
AU  - Shaoyang Zhang
AU  - Jiabin Wei
AU  - Yanying Shang
PY  - 2023
DA  - 2023/12/04
TI  - Research on Personalized News Recommendation Model Based on Knowledge Graph
BT  - Proceedings of the 3rd International Conference on Digital Economy and Computer Application (DECA 2023)
PB  - Atlantis Press
SP  - 325
EP  - 335
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-304-7_35
DO  - 10.2991/978-94-6463-304-7_35
ID  - Li2023
ER  -