Semantic-Enriched Latent Factor Models with Sparse Data for Enhanced Performance of E-Commerce Recommender Systems
Received: 19 August 2025 | Revised: 2 October 2025 and 17 October 2025 | Accepted: 19 October 2025 | Online: 9 February 2026
Corresponding author: Jaeni Jaeni
Abstract
Recommender systems play a vital role in e-commerce by reducing information overload and providing personalized suggestions. However, conventional collaborative filtering methods often suffer from data sparsity and a limited ability to capture temporal user dynamics and user behavior. To address these limitations, this study proposes SEMAR-LF, a hybrid model that integrates Probabilistic Matrix Factorization (PMF), Long Short-Term Memory (LSTM), and semantic embeddings derived from product reviews. In this framework, textual reviews are preprocessed into semantic vectors, user-item interactions are temporally ordered, and sequential patterns are modeled through LSTM to generate dynamic user representations, which are then combined with item factors in the PMF framework for rating prediction. Experiments on the MovieLens ML-1M and ML-10M benchmark datasets show that SEMAR-LF consistently outperforms baseline models such as PMF, CTR, CDL, and ConvMF. The best performance was achieved on ML-10M with an RMSE of 0.79020, reflecting a 44.62% improvement over PMF in sparse conditions. As a complementary pilot, a lightweight SEMAR‑ATT variant (PMF+RoBERTa‑based content fusion) is presented that attains RMSE of 0.8565 and MAE of 0.6655 against a global‑mean baseline (RMSE 1.0662 and MAE 0.8640), validating the effectiveness of semantic fusion even with simulated features. These results highlight the practicality and extensibility of semantic-enriched latent factorization for real-world recommendation systems.
Keywords:
collaborative filtering, probabilistic matrix factorization, e-commerce recommender system, word embedding, semantic regularization, contextual word representationDownloads
References
Q. Zhang, J. Lu, and Y. Jin, "Artificial intelligence in recommender systems," Complex & Intelligent Systems, vol. 7, no. 1, pp. 439–457, Feb. 2021. DOI: https://doi.org/10.1007/s40747-020-00212-w
S. Airen and J. Agrawal, "Movie Recommender System Using Parameter Tuning of User and Movie Neighbourhood via Co-Clustering," Procedia Computer Science, vol. 218, pp. 1176–1183, 2023. DOI: https://doi.org/10.1016/j.procs.2023.01.096
S. Sharma and A. A. Waoo, "Customer Behavior Analysis in E-Commerce using Machine Learning Approach: A Survey," International Journal of Scientific Research in Computer Scirnce, Engineering, and Information Technology, vol. 10, no. 2, pp. 163–170, 2023.
M. Sharma, R. Mittal, A. Bharati, D. Saxena, and A. K. Singh, "A Survey and Classification on Recommendation Systems," in Big Data, Machine Learning, and Applications, vol. 1053, M. D. Borah, D. S. Laiphrakpam, N. Auluck, and V. E. Balas, Eds. Springer Nature Singapore, 2024, pp. 569–585. DOI: https://doi.org/10.1007/978-981-99-3481-2_44
P. M. Alamdari, N. J. Navimipour, M. Hosseinzadeh, A. A. Safaei, and A. Darwesh, "A Systematic Study on the Recommender Systems in the E-Commerce," IEEE Access, vol. 8, pp. 115694–115716, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3002803
F. Ricci, L. Rokach, and B. Shapira, Eds., Recommender Systems Handbook. Boston, MA, USA: Springer US, 2015. DOI: https://doi.org/10.1007/978-1-4899-7637-6
D. Jannach, P. Pu, F. Ricci, and M. Zanker, "Recommender systems: Past, present, future," AI Magazine, vol. 42, no. 3, pp. 3–6, Sept. 2021. DOI: https://doi.org/10.1609/aimag.v42i3.18139
H. Ko, S. Lee, Y. Park, and A. Choi, "A Survey of Recommendation Systems: Recommendation Models, Techniques, and Application Fields," Electronics, vol. 11, no. 1, Jan. 2022, Art. no. 141. DOI: https://doi.org/10.3390/electronics11010141
K. Benabbes, K. Housni, A. E. Mezouary, and A. Zellou, "Recommendation System Issues, Approaches and Challenges Based on User Reviews," Journal of Web Engineering, Apr. 2022. DOI: https://doi.org/10.13052/jwe1540-9589.2143
S. G. L. Mirthika and B. Sivakumar, "Enhancing Hybrid Filtering for Evolving Recommender Systems: Dealing with Data Sparsity and Cold Start Problems," in 2024 Second International Conference on Inventive Computing and Informatics (ICICI), Bangalore, India, June 2024, pp. 141–146. DOI: https://doi.org/10.1109/ICICI62254.2024.00033
Y. Koren, R. Bell, and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems," Computer, vol. 42, no. 8, pp. 30–37, Aug. 2009. DOI: https://doi.org/10.1109/MC.2009.263
B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk, "Session-based Recommendations with Recurrent Neural Networks." arXiv, Mar. 29, 2016.
W. C. Kang and J. McAuley, "Self-Attentive Sequential Recommendation," in 2018 IEEE International Conference on Data Mining (ICDM), Singapore, Nov. 2018, pp. 197–206. DOI: https://doi.org/10.1109/ICDM.2018.00035
F. Sun et al., "BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer," in Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, China, Nov. 2019, pp. 1441–1450. DOI: https://doi.org/10.1145/3357384.3357895
S. Lee, J. Ahn, and N. Kim, "Embedding Enhancement Method for LightGCN in Recommendation Information Systems," Electronics, vol. 13, no. 12, June 2024, Art. no. 2282. DOI: https://doi.org/10.3390/electronics13122282
A. Mnih and R. Salakhutdinov, "Probabilistic matrix factorization. in advances in neural information processing systems," in Advances in neural information processing systems, 2007.
H. Wang and W. J. Li, "Relational Collaborative Topic Regression for Recommender Systems," IEEE Transactions on Knowledge and Data Engineering, vol. 27, no. 5, pp. 1343–1355, May 2015. DOI: https://doi.org/10.1109/TKDE.2014.2365789
D. Kim, C. Park, J. Oh, S. Lee, and H. Yu, "Convolutional Matrix Factorization for Document Context-Aware Recommendation," in Proceedings of the 10th ACM Conference on Recommender Systems, Boston, MA, USA, Sept. 2016, pp. 233–240. DOI: https://doi.org/10.1145/2959100.2959165
C. Y. Wu, A. Ahmed, A. Beutel, A. J. Smola, and H. Jing, "Recurrent Recommender Networks," in Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, Cambridge United Kingdom, Feb. 2017, pp. 495–503. DOI: https://doi.org/10.1145/3018661.3018689
H. Wu, Z. Zhang, K. Yue, B. Zhang, J. He, and L. Sun, "Dual-regularized matrix factorization with deep neural networks for recommender systems," Knowledge-Based Systems, vol. 145, pp. 46–58, Apr. 2018. DOI: https://doi.org/10.1016/j.knosys.2018.01.003
J. McAuley and J. Leskovec, "Hidden factors and hidden topics: understanding rating dimensions with review text," in Proceedings of the 7th ACM conference on Recommender systems, Hong Kong, China, Oct. 2013, pp. 165–172. DOI: https://doi.org/10.1145/2507157.2507163
H. Wang, N. Wang, and D. Y. Yeung, "Collaborative Deep Learning for Recommender Systems," in Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia, Aug. 2015, pp. 1235–1244. DOI: https://doi.org/10.1145/2783258.2783273
A. Gupta and P. Shrinath, "Link Prediction based on bipartite graph for recommendation system using optimized SVD++," Procedia Computer Science, vol. 218, pp. 1353–1365, 2023. DOI: https://doi.org/10.1016/j.procs.2023.01.114
J. Wu et al., "IT-PMF: A Novel Community E-Commerce Recommendation Method Based on Implicit Trust," Mathematics, vol. 10, no. 14, July 2022, Art. no. 2406. DOI: https://doi.org/10.3390/math10142406
S. Peng, K. Sugiyama, and T. Mine, "SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation," in Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA, Oct. 2022, pp. 1625–1634. DOI: https://doi.org/10.1145/3511808.3557462
X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T. S. Chua, "Neural Collaborative Filtering," in Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, Apr. 2017, pp. 173–182. DOI: https://doi.org/10.1145/3038912.3052569
L. Zhang, S. Chen, G. Fan, H. Wu, H. Chen, and Z. Feng, "A time-aware developer recommendation approach based on multi-feature fusion," Applied Soft Computing, vol. 169, Jan. 2025, Art. no. 112609. DOI: https://doi.org/10.1016/j.asoc.2024.112609
S. Medjroud, N. Dennouni, and M. Loukam, "Point of Interest Recommendation using Implicit Trust based on Combining Ratings and Check-ins of Smartphone Users," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21249–21256, Apr. 2025. DOI: https://doi.org/10.48084/etasr.9965
Y. Cai, W. Ke, E. Cui, and F. Yu, "A deep recommendation model of cross-grained sentiments of user reviews and ratings," Information Processing & Management, vol. 59, no. 2, Mar. 2022, Art. no. 102842. DOI: https://doi.org/10.1016/j.ipm.2021.102842
Y. Liu et al., "RoBERTa: A Robustly Optimized BERT Pretraining Approach." arXiv, July 26, 2019.
Y. Zhuang and J. Kim, "A BERT-Based Multi-Criteria Recommender System for Hotel Promotion Management," Sustainability, vol. 13, no. 14, July 2021, Art. no. 8039. DOI: https://doi.org/10.3390/su13148039
W. Yuan, H. Wang, X. Yu, N. Liu, and Z. Li, "Attention-based context-aware sequential recommendation model," Information Sciences, vol. 510, pp. 122–134, Feb. 2020. DOI: https://doi.org/10.1016/j.ins.2019.09.007
X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, "LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation," in Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, July 2020, pp. 639–648. DOI: https://doi.org/10.1145/3397271.3401063
K. Zhou et al., "S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization," in Proceedings of the 29th ACM International Conference on Information & Knowledge Management, Oct. 2020, pp. 1893–1902. DOI: https://doi.org/10.1145/3340531.3411954
F. M. Harper and J. A. Konstan, "The MovieLens Datasets: History and Context," ACM Transactions on Interactive Intelligent Systems, vol. 5, no. 4, pp. 1–19, Jan. 2016. DOI: https://doi.org/10.1145/2827872
Z. Khan, N. Iltaf, H. Afzal, and H. Abbas, "Enriching Non-negative Matrix Factorization with Contextual Embeddings for Recommender Systems," Neurocomputing, vol. 380, pp. 246–258, Mar. 2020. DOI: https://doi.org/10.1016/j.neucom.2019.09.080
M. O. Ayemowa, R. Ibrahim, and Y. A. Bena, "A systematic review of the literature on deep learning approaches for cross-domain recommender systems," Decision Analytics Journal, vol. 13, Dec. 2024, Art. no. 100518. DOI: https://doi.org/10.1016/j.dajour.2024.100518
Z. Batmaz, A. Yurekli, A. Bilge, and C. Kaleli, "A review on deep learning for recommender systems: challenges and remedies," Artificial Intelligence Review, vol. 52, no. 1, pp. 1–37, June 2019. DOI: https://doi.org/10.1007/s10462-018-9654-y
Downloads
How to Cite
License
Copyright (c) 2025 Jaeni Jaeni, Purwanto Purwanto, Budi Warsito
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- 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 acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
