How Much do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations
Resumo
Incorporating textual reviews into a Recommender System has become a prominent strategy for enriching collaborative signals with semantic information. However, the actual contribution of review-derived representations remains an open question, particularly when strong collaborative baselines are employed. In this work, we systematically investigate the impact of textual information on Matrix Factorization by introducing and comparing three enrichment strategies over a common collaborative backbone. First, we propose a learnable gating mechanism that adaptively balances collaborative and textual signals during training. This mechanism is applied to two distinct review representations: (i) aggregated topic profiles extracted from user and item histories, and (ii) full text embedding representations derived from reviews. Additionally, we explore a cross-attention mechanism that identifies and emphasizes the most informative dimensions of the textual representation before fusion with collaborative factors. We evaluate six variants: pure, enriched with topic profiles and text via gating; enriched with topics and text via gating; and enhanced with cross-attention over textual features. Experiments across multiple review-based datasets reveal that although adaptive fusion mechanisms improve representation flexibility, the marginal contribution of textual signals remains limited compared to the collaborative backbone. These findings suggest that, under typical rating-prediction settings, collaborative information continues to dominate performance, raising important considerations for the effective integration of semantic review signals into recommendation models.
Palavras-chave:
Recommendations, review-aware, collaborative filtering, topic-based
Referências
da Silva, D., Pires, J., and Durão, F. (2025). Exploiting surrogate submodular and costeffective lazy forward algorithms for calibrated recommendations. In Anais do XL Simpósio Brasileiro de Bancos de Dados, pages 98–111, Porto Alegre, RS, Brasil. SBC.
Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7(1):1–30.
Grootendorst, M. (2022). Bertopic: Neural topic modeling with a class-based tf-idf procedure.
Hasan, E., Rahman, M., Ding, C., Huang, J. X., and Raza, S. (2024). Review-based Recommender Systems: A Survey of Approaches, Challenges and Future Perspectives. Proceedings of the ACM on Measurement and Analysis of Computing Systems, XX(X).
Jurdi, W. A., Abdo, J. B., Demerjian, J., and Makhoul, A. (2021). Critique on natural noise in recommender systems. ACM Trans. Knowl. Discov. Data, 15(5).
Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., and Zhang, M. (2023). Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281.
Lima, M., Silva, E., and da Silva, A. (2024). Um estudo sobre o uso de modelos de linguagem abertos na tarefa de recomendação de próximo item. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados, pages 510–522, Porto Alegre, RS, Brasil. SBC.
Liu, D., Li, J., Du, B., Chang, J., and Gao, R. (2019). Daml: Dual attention mutual learning between ratings and reviews for item recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’19, page 344–352, New York, NY, USA. Association for Computing Machinery.
Liu, Y. and Miyazaki, J. (2023). Knowledge-aware attentional neural network for review-based movie recommendation with explanations.
Ma, H., Xie, R., Meng, L., Feng, F., Du, X., Sun, X., Kang, Z., and Meng, X. (2025). Negative sampling in recommendation: A survey and future directions.
Ricci, F., Rokach, L., and Shapira, B., editors (2022). Recommender Systems Handbook: Third Edition. Springer US, United States, 3 edition. Publisher Copyright: © Springer Science+Business Media, LLC, part of Springer Nature 2011, 2015, 2022.
Sachdeva, N. and McAuley, J. (2020). How useful are reviews for recommendation? a critical review and potential improvements. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’20, page 1845–1848, New York, NY, USA. Association for Computing Machinery.
Silva, E., Pires, J., Dantas, D., Oliveira, M., and Durão, F. (2025a). A gated review attention framework for topics in graph-based recommenders. In Proceedings of the 31st Brazilian Symposium on Multimedia and the Web, pages 19–27, Porto Alegre, RS, Brasil. SBC.
Silva, F., Filho, S. A., Paradeda, R., and Silva, L. (2025b). Análise de sentimentos em avaliações de livros utilizando a api gemini para recomendação personalizada. In Anais do XL Simpósio Brasileiro de Bancos de Dados, pages 671–684, Porto Alegre, RS, Brasil. SBC.
Son, J., Kim, H., and Kim, S. W. (2025). Rating-Aware Homogeneous Review Graphs and User Likes/Dislikes Differentiation for Effective Recommendations. SIGIR 2025 - Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2070–2080.
Tan, C. H., Zheng, H., Wang, J., Lin, Z., Feng, S., Zhan, H., Li, X., and Senthilnath, J. (2025). Do reviews matter for recommendations in the era of large language models? ArXiv, abs/2512.12978.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. u., and Polosukhin, I. (2017). Attention is all you need. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc.
Zheng, L., Noroozi, V., and Yu, P. S. (2017). Joint deep modeling of users and items using reviews for recommendation. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, WSDM ’17, page 425–434, New York, NY, USA. Association for Computing Machinery.
Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7(1):1–30.
Grootendorst, M. (2022). Bertopic: Neural topic modeling with a class-based tf-idf procedure.
Hasan, E., Rahman, M., Ding, C., Huang, J. X., and Raza, S. (2024). Review-based Recommender Systems: A Survey of Approaches, Challenges and Future Perspectives. Proceedings of the ACM on Measurement and Analysis of Computing Systems, XX(X).
Jurdi, W. A., Abdo, J. B., Demerjian, J., and Makhoul, A. (2021). Critique on natural noise in recommender systems. ACM Trans. Knowl. Discov. Data, 15(5).
Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., and Zhang, M. (2023). Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281.
Lima, M., Silva, E., and da Silva, A. (2024). Um estudo sobre o uso de modelos de linguagem abertos na tarefa de recomendação de próximo item. In Anais do XXXIX Simpósio Brasileiro de Bancos de Dados, pages 510–522, Porto Alegre, RS, Brasil. SBC.
Liu, D., Li, J., Du, B., Chang, J., and Gao, R. (2019). Daml: Dual attention mutual learning between ratings and reviews for item recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’19, page 344–352, New York, NY, USA. Association for Computing Machinery.
Liu, Y. and Miyazaki, J. (2023). Knowledge-aware attentional neural network for review-based movie recommendation with explanations.
Ma, H., Xie, R., Meng, L., Feng, F., Du, X., Sun, X., Kang, Z., and Meng, X. (2025). Negative sampling in recommendation: A survey and future directions.
Ricci, F., Rokach, L., and Shapira, B., editors (2022). Recommender Systems Handbook: Third Edition. Springer US, United States, 3 edition. Publisher Copyright: © Springer Science+Business Media, LLC, part of Springer Nature 2011, 2015, 2022.
Sachdeva, N. and McAuley, J. (2020). How useful are reviews for recommendation? a critical review and potential improvements. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’20, page 1845–1848, New York, NY, USA. Association for Computing Machinery.
Silva, E., Pires, J., Dantas, D., Oliveira, M., and Durão, F. (2025a). A gated review attention framework for topics in graph-based recommenders. In Proceedings of the 31st Brazilian Symposium on Multimedia and the Web, pages 19–27, Porto Alegre, RS, Brasil. SBC.
Silva, F., Filho, S. A., Paradeda, R., and Silva, L. (2025b). Análise de sentimentos em avaliações de livros utilizando a api gemini para recomendação personalizada. In Anais do XL Simpósio Brasileiro de Bancos de Dados, pages 671–684, Porto Alegre, RS, Brasil. SBC.
Son, J., Kim, H., and Kim, S. W. (2025). Rating-Aware Homogeneous Review Graphs and User Likes/Dislikes Differentiation for Effective Recommendations. SIGIR 2025 - Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2070–2080.
Tan, C. H., Zheng, H., Wang, J., Lin, Z., Feng, S., Zhan, H., Li, X., and Senthilnath, J. (2025). Do reviews matter for recommendations in the era of large language models? ArXiv, abs/2512.12978.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. u., and Polosukhin, I. (2017). Attention is all you need. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc.
Zheng, L., Noroozi, V., and Yu, P. S. (2017). Joint deep modeling of users and items using reviews for recommendation. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, WSDM ’17, page 425–434, New York, NY, USA. Association for Computing Machinery.
Publicado
08/09/2026
Como Citar
DA SILVA, Eduardo Ferreira; OLIVEIRA, Mayki dos Santos; PIRES, Joel Machado; BOAVENTURA, Denis Dantas; DURÃO, Frederico Araújo.
How Much do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 29-42.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2026.249133.
