Enhancing Recommendation Systems via Aspect-Level Sentiment Analysis for Identifying Unreliable Reviews

Authors

El Mehdi Lghaouch
Laboratory of Information Technology and Modeling, Faculty of Sciences Ben M’Sik, Hassan II University, Casablanca
Fatima Zahra Abbour
Laboratory of Information Technology and Modeling, Faculty of Sciences Ben M’Sik, Hassan II University, Casablanca
Soumaya Ounacer
Laboratory of Information Technology and Modeling, Faculty of Sciences Ben M’Sik, Hassan II University, Casablanca
Soufiane Ardchir
National School of Management and Marketing, Hassan II University, Casablanca
Mohamed Azzouazi
Laboratory of Information Technology and Modeling, Faculty of Sciences Ben M’Sik, Hassan II University, Casablanca
DOI: https://doi.org/10.52549/ijeei.v14i2.7834
Download PDF
Published: 19-04-2026 • Issue: Vol. 14 No. 2: June 2026 • Section: Regular paper

Abstract

User-generated reviews are an important source of information for e-commerce recommendation systems. However, reviews may contain conflicting opinions across product aspects such as quality, price, and delivery, which can weaken both review-level trust and aspect-level signals. To address this issue, we propose AspectGuard, a filtering framework based on Aspect-Based Sentiment Analysis (ABSA) and a Sentiment Divergence Score (SDS) that quantifies disagreement across aspect-level sentiments within a review. Reviews with high divergence are identified as potentially unreliable and excluded before constructing recommendation profiles. To isolate the contribution of the proposed filtering mechanism, we compare the same content-based recommendation model with and without AspectGuard filtering. Experiments conducted on a subset of the Amazon Reviews 2023 Electronics dataset show that the proposed filtering strategy improves both rating prediction and ranking quality. These results indicate that aspect level sentiment divergence can serve as an effective signal for identifying unreliable reviews and improving the reliability of recommendation systems.
Keywords: Artificial Intelligence; Sentiment Analysis; Review Filtering; Recommendation Systems; Aspect Analysis; E-Commerce Reviews

References

M. Meftah, S. Ounacer, and M. Azzouazi, “Enhancing customer engagement in loyalty programs through AI-powered market basket prediction using machine learning algorithms,†in Synthesis Lectures on Engineering, Science, and Technology. Cham: Springer, 2024, pp. 319–337. doi: 10.1007/978-3-031-50300-9_18.

C. C. Aggarwal, Recommender Systems: The Textbook. Springer, 2016.

H. Aitelbour, S. Ounacer, Y. Elghomari, H. Jihal, and M. Azzouazi, “A crime prediction model based on spatial and temporal data,†Periodicals of Engineering and Natural Sciences, vol. 6, no. 2, pp. 360–364, 2018.

A. M. S. Osman, Z. A. El-Gohary, and A. E. D. M. El-Nakeeb, “The role of trust in e-commerce recommendation systems: a systematic literature review,†International Journal of Computer Applications, vol. 174, no. 43, pp. 24–32, 2021.

S. M. AL-Ghuribi and S. A. Mohd Noah, “A review of aspect-based sentiment analysis: taxonomy, methods, datasets, and challenges,†arXiv preprint arXiv:2107.03433, 2021.

E. M. Lghaouch, S. Ounacer, S. Ardchir, and M. Azzouazi, “Enhancing sentiment analysis through topic modeling: Comprehensive overview,†in Studies in Systems, Decision and Control, vol. 565. Cham: Springer, 2024, pp. 161–179. doi: 10.1007/978-3-031-70996-8_8.

M. Hu and B. Liu, “Mining and summarizing customer reviews,†in Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2004, pp. 168–177.

W. Zhang, S. A. G. M. Stilo, and T. L. A. van der Weide, “A survey of aspect-level sentiment analysis: methods, performance, and applications,†Knowledge and Information Systems, vol. 64, pp. 2439–2486, 2022.

L. Qu, G. Ifrim, and G. Weikum, “The bag-of-opinions method for review rating prediction from sparse text,†in Proceedings of the 23rd International Conference on Computational Linguistics (COLING), 2010, pp. 913–921.

J. Liu, Y. Zhang, Y. Wang, L. Guo, and B. Li, “A review polarity-wise recommender,†in Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2021, pp. 2165–2169.

P. Resnick and H. R. Varian, “Recommender systems,†Communications of the ACM, vol. 40, no. 3, pp. 56–58, 1997.

N. Jindal and B. Liu, “Opinion spam and analysis,†in Proceedings of the 2008 International Conference on Web Search and Data Mining (WSDM), 2008, pp. 219–230.

S. M. Kim, P. Pantel, T. Chklovski, and M. Pennacchiotti, “Automatically assessing review helpfulness,†in Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2006, pp. 423–430.

P. Phukon, “Detecting fake reviews using aspect based sentiment analysis and graph,†Master’s Project, San Jose State University, 2024.

A. Periasamy, R. Karthik, and V. Subramanian, “Finding fake reviews in e-commerce platforms by using hybrid algorithms,†arXiv preprint arXiv:2404.06339, 2024.

A. Karmakar and J. Hawkins, “Enhanced review detection and recognition: A platform-agnostic approach with application to online commerce,†arXiv preprint arXiv:2405.06704, 2024.

T. T. Thet, C. W. Oo, and S. Phyo, “Systematic reviews in sentiment analysis: A tertiary study,†Artificial Intelligence Review, vol. 54, no. 8, pp. 5999–6033, 2021.

P. Kumar, A. Sharma, and D. K. Sharma, “Aspect-based sentiment classification of user reviews to understand customer satisfaction of e-commerce platforms,†Electronic Commerce Research, published online Feb. 20, 2025. doi: 10.1007/s10660-025-09721-3.

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 (RecSys), 2013, pp. 165–172.

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 (WWW), 2017, pp. 173–182. doi: 10.1145/3038912.3052569.

J. Chen, H. Huang, Y. Tian, C. Qu, and L. Wu, “Multi-aspect user-interest model based on sentiment analysis and uncertainty theory for recommender systems,†Electronic Commerce Research and Applications, vol. 28, pp. 126–140, 2018.

J. Ren, S. Ma, H. Chen, and L. Liu, “A knowledge-enhanced recommender system with aspect-level information,†Expert Systems with Applications, vol. 138, p. 112810, 2019.

H. P. Chan, W. Chen, and I. King, “A unified dual-view model for review summarization and sentiment classification with inconsistency loss,†arXiv preprint arXiv:2006.01592, 2020.

R. Gupta, A. Kumar, P. K. Sharma, and H. K. Tripathi, “Recent state-of-the-art of fake review detection: a comprehensive review,†The Knowledge Engineering Review, vol. 39, p. e8, 2024. doi: 10.1017/S0269888924000054.

J. McAuley et al., “Amazon Reviews 2023 Dataset,†2023. Available: https://huggingface.co/datasets/McAuley-Lab/Amazon-Reviews-2023.

P. He, X. Liu, J. Gao, and W. Chen, “DeBERTa: Decoding-enhanced BERT with Disentangled Attention,†arXiv preprint arXiv:2006.03654, 2021.

M. Honnibal, I. Montani, S. Van Landeghem, and A. Boyd, “spaCy: Industrial-strength Natural Language Processing in Python,†2020. Available: https://spacy.io.

How to Cite

[1]
E. M. Lghaouch, F. Z. Abbour, S. Ounacer, S. Ardchir, and M. Azzouazi, “Enhancing Recommendation Systems via Aspect-Level Sentiment Analysis for Identifying Unreliable Reviews”, IJEEI, vol. 14, no. 2, pp. 435–445, Apr. 2026, doi: 10.52549/ijeei.v14i2.7834.