* Corresponding Author
Hide
Show all
Enhancing Neural Collaborative Filtering with Metadata for Book Recommender System
https://doi.org/10.22146/ijccs.103611 Z. K. A. Baizal(1*), Putri Ayu Sedyo Mukti(2)
(1) Telkom University
(2) Telkom University
(*) Corresponding Author
Abstract
In the era of big data, there is an exponential increase in data that provides information overload problems, one of which is in the field of e-commerce. In previous studies, an Amazon book recommender system has been successfully developed that performs well. However, its accuracy still has the potential to be improved. This research proposes the Feature Enhanced Neural Collaborative Filtering (FENCF) Method which is a modification of the Neural collaborative filtering method to improve accuracy and handle item cold starts. The FENCF method utilizes genre metadata information as item attributes that are preprocessed using sentence BERT and K-means. Experiments were conducted using the Amazon book dataset. The test results show that FENCF can improve the RMSE by 11% and MAE by 10% compared to the best competitor, NCF. In addition, in testing of item cold starts, FENCF also produces lower MAE values in all data testing scenarios compared to the NCF method. The results show that proposed method is proven to be superior in handling item cold starts and improving rating accuracy compared to the baseline method, making it a promising solution for creating a more accurate and relevant book recommender system
Keywords
Full Text:
PDFReferences
Yang, X., & Shi, Y. (2020). Self-attention-based group recommendation. 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). https://doi.org/10.1109/itnec48623.2020.9085011 [2] Nahta, R., Meena, Y. K., Gopalani, D., & Chauhan, G. S. (2021). Embedding metadata using deep collaborative filtering to address the cold start problem for the rating prediction task. Multimedia Tools and Applications, 80(12). https://doi.org/10.1007/s11042-021-10529-4 [3] Jena, K. K., Bhoi, S. K., Mallick, C., Jena, S. R., Kumar, R., Long, H. V., & Son, N. T. K. (2022). Neural model based collaborative filtering for movie recommender system. International Journal of Information Technology (Singapore), 14(4). https://doi.org/10.1007/s41870-022-00858-4 [4] Margaris, D., Vassilakis, C., & Spiliotopoulos, D. (2020). What makes a review a reliable rating in recommender systems? Information Processing and Management, 57(6). https://doi.org/10.1016/j.ipm.2020.102304 [5] Kharroubi, S., Dahmani, Y., & Nouali, O. (2022). Improving collaborative recommendation based on item weight link prediction. Turkish Journal of Electrical Engineering and Computer Sciences, 30(1). https://doi.org/10.3906/elk-2008-26 [6] Gao, C., Yao, Q., Jin, D., & Li, Y. (2021). Efficient Data-specific Model Search for Collaborative Filtering. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/3447548.3467399 [7] Addanki, M., Saraswathi, S., SLAVAKKAM, D. B., Challagundla, R. B., & Pamula, R. (2023). Integrating Sentiment Analysis in Book Recommender System by using Rating Prediction and DBSCAN Algorithm with Hybrid Filtering Technique. [8] Karabila, I., Darraz, N., El-Ansari, A., Alami, N., & El Mallahi, M. (2023). Enhancing Collaborative Filtering-Based Recommender System Using Sentiment Analysis. Future Internet, 15(7). https://doi.org/10.3390/fi15070235 [9] Panda, D. K., & Ray, S. (2022). Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature review. Journal of Intelligent Information Systems, 59(2). https://doi.org/10.1007/s10844-022-00698-5 [10] “Amazon Books Reviews,” www.kaggle.com. https://www.kaggle.com/datasets/mohamedbakhet/amazon-books-reviews [11] Koren, Y., & Bell, R. (2021). Advances in Collaborative Filtering - Recommender Systems Handbook. Recommender Systems Handbook. [12] Lee, H. C., Kim, Y. S., & Kim, S. W. (2024). Real-Time Movie Recommendation: Integrating Persona-Based User Modeling with NMF and Deep Neural Networks. Applied Sciences (Switzerland), 14(3). https://doi.org/10.3390/app14031014 [13] Yu, J., Yin, H., Xia, X., Chen, T., Li, J., & Huang, Z. (2024). Self-Supervised Learning for Recommender Systems: A Survey. IEEE Transactions on Knowledge and Data Engineering, 36(1). https://doi.org/10.1109/TKDE.2023.3282907 [14] Liang, W., Fan, Z., Liang, Y., & Jia, J. (2023). Cross-Attribute Matrix Factorization Model with Shared User Embedding. arXiv preprint arXiv:2308.07284.
DOI: https://doi.org/10.22146/ijccs.103611
Article Metrics
Abstract views : 2
| 
views : 1
Refbacks
- There are currently no refbacks.
Copyright (c) 2025 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
View My Stats1