Advances in Engineering Innovation
Vol. 8, 28 June 2024
Open
Access | Article
Design of a news recommendation model based on collaborative filtering and LSTM
* Author to whom correspondence should be addressed.
Abstract
This paper aims to design a news recommendation model based on user preferences to address the issues in recommendation systems under large datasets. Initially, four datasets—click_history, news, news_embedding, and user_predict—were integrated into a single table, followed by data cleaning and feature engineering. Due to the large volume of data, this paper proposes necessary data filtering for the training and testing sets, utilizing temporal data to construct user feature vectors and news feature vectors. One challenge is how to effectively integrate user preferences and news features into the model to avoid overfitting or underfitting. In the model design and building phase, different methods were attempted to merge the information of users and news. Ultimately, the user preference features were processed using a fully connected layer, and the news embedding vectors were handled using an LSTM model. These two data parts were then combined into another fully connected layer, using ReLU as the activation function and CELoss as the loss function. Subsequently, the model's hyperparameters were adjusted and evaluated, achieving favorable model performance. The prediction accuracy for recommending news to users in user_predict was calculated as an evaluation criterion. Finally, this paper proposes directions for generalization and optimization in three aspects: data processing, model design, and experimental design. This includes data processing methods, potential improvements or mechanisms that could be incorporated into the model, and hyperparameter tuning. The paper primarily proposes data filtering to solve the problem of excessive data scale, which may aid in addressing recommendation system issues under large-scale datasets.
Keywords
machine Learning, collaborative filtering, text classification, LSTM
References
1. Tian, X., Ding, Q., Liao, Z. H., et al. (2021). A review of news recommendation algorithms based on deep learning. Journal of Computer Science and Exploration, 15(06), 971-998.
2. Xue, C. X., & Zhang, Y. F. (2013). A review of Chinese text classification research in the news domain. Library and Information Service, 57(14), 134-139.
3. Chai, Z. H. (2022). Bi-LSTM commodity recommendation system based on word embedding [Doctoral dissertation, Hebei University of Science and Technology]. https://doi.org/10.27107/d.cnki.ghbku.2021.000685
4. S. N. K., & G. D. T. (2022). Dynamic light weight recommendation system for social networking analysis using a hybrid LSTM-SVM classifier algorithm. Optical Memory and Neural Networks, 31(1).
5. Wu, G. D. (2021). Research on personalized item recommendation based on deep learning [Doctoral dissertation, Donghua University]. https://doi.org/10.27012/d.cnki.gdhuu.2020.000335
6. Liu, G. (2023). Research on news recommendation methods based on knowledge graphs and personalized attention mechanisms [Doctoral dissertation, Hubei University]. https://doi.org/10.27130/d.cnki.ghubu.2023.000534
7. Ma, H. W., Zhang, G. W., & Li, P. (2009). A review of collaborative filtering recommendation algorithms. Journal of Mini & Micro Computer Systems, 30(07), 1282-1288.
8. Zhao, W., Lin, N., Han, Y., et al. (2016). An improved collaborative filtering algorithm based on K-means clustering. Journal of Anhui University (Natural Science Edition), 40(02), 32-36.
9. Reham, A., Halah, A., & Amaal, A. (2023). Context-aware news recommendation system: Incorporating contextual information and collaborative filtering techniques. International Journal of Computational Intelligence Systems, 16(1).
10. Yang, W., Tang, R., & Lu, L. (2016). News recommendation methods based on the integration of content-based recommendation and collaborative filtering. Journal of Computer Applications, 36(02), 414-418.
11. Ai, P. Q. (2017). Research on personalized news recommendation systems based on temporal behavior and tag relationships [Doctoral dissertation, Tianjin University of Technology].
Data Availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).
- Volume Title
- ISBN (Print)
- ISBN (Online)
- Published Date
- 28 June 2024
- Series
- Advances in Engineering Innovation
- ISSN (Print)
- 2977-3903
- ISSN (Online)
- 2977-3911
- DOI
- 10.54254/2977-3903/8/2024078
- Copyright
- 28 June 2024
- Open Access
- This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited