IDEAS home Printed from https://ideas.repec.org/a/eee/jbrese/v201y2025ics0148296325005648.html

A preference learning method to estimate consumer preferences from online reviews

Author

Listed:
  • Wu, Xingli
  • Liao, Huchang

Abstract

Accurate prediction of consumer preferences aids numerous marketing efforts on e-commerce platforms, as it identifies which product attributes have an impact and how they influence a consumer’s purchase decisions. This study proposes a preference learning method for the automated extraction of consumer preferences from online reviews. A preference model, grounded in the multi-attribute value theory, is proposed to delineate the preference structures of consumers. This model bridges overall ratings and attribute-level reviews while incorporating considerations of attribute importance, compensation effects between attributes, and inconsistent sets of attributes across reviews. A classification algorithm is presented based on an optimization model to estimate preference parameters within the preference model. Its prediction accuracy is evaluated using k-fold cross-validation, while its robustness is measured through simulations. Case studies in the hotel, restaurant, and automobile domains validate that the proposed method generates transparent preference models with robust predictive performance and clear interpretations.

Suggested Citation

  • Wu, Xingli & Liao, Huchang, 2025. "A preference learning method to estimate consumer preferences from online reviews," Journal of Business Research, Elsevier, vol. 201(C).
    • Handle: RePEc:eee:jbrese:v:201:y:2025:i:c:s0148296325005648
    DOI: 10.1016/j.jbusres.2025.115741
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0148296325005648
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.jbusres.2025.115741?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Vairetti, Carla & Aránguiz, Ignacio & Maldonado, Sebastián & Karmy, Juan Pablo & Leal, Alonso, 2024. "Analytics-driven complaint prioritisation via deep learning and multicriteria decision-making," European Journal of Operational Research, Elsevier, vol. 312(3), pages 1108-1118.
    2. Wu, Xingli & Liao, Huchang, 2025. "Determining investment allocation strategies to improve consumer satisfaction based on a preference learning model," Journal of Retailing and Consumer Services, Elsevier, vol. 82(C).
    3. James S. Dyer & James E. Smith, 2021. "Innovations in the Science and Practice of Decision Analysis: The Role of Management Science," Management Science, INFORMS, vol. 67(9), pages 5364-5378, September.
    4. Anning Wang & Qiang Zhang & Shuangyao Zhao & Xiaonong Lu & Zhanglin Peng, 2020. "A review-driven customer preference measurement model for product improvement: sentiment-based importance–performance analysis," Information Systems and e-Business Management, Springer, vol. 18(1), pages 61-88, March.
    5. Decker, Reinhold & Trusov, Michael, 2010. "Estimating aggregate consumer preferences from online product reviews," International Journal of Research in Marketing, Elsevier, vol. 27(4), pages 293-307.
    6. Jian-Wu Bi & Yang Liu & Zhi-Ping Fan & Erik Cambria, 2019. "Modelling customer satisfaction from online reviews using ensemble neural network and effect-based Kano model," International Journal of Production Research, Taylor & Francis Journals, vol. 57(22), pages 7068-7088, November.
    7. Gilbert, Hugo & Ouaguenouni, Mohamed & Öztürk, Meltem & Spanjaard, Olivier, 2025. "Robust ordinal regression for subsets comparisons with interactions," European Journal of Operational Research, Elsevier, vol. 320(1), pages 146-159.
    8. Jiapeng Liu & Miłosz Kadziński & Xiuwu Liao, 2023. "Modeling Contingent Decision Behavior: A Bayesian Nonparametric Preference-Learning Approach," INFORMS Journal on Computing, INFORMS, vol. 35(4), pages 764-785, July.
    9. König, Tatjana Maria & Hein, Nika & Nimsgern, Vivien, 2022. "A value perspective on online review platforms: Profiling preference structures of online shops and traditional companies," Journal of Business Research, Elsevier, vol. 145(C), pages 387-401.
    10. Jacquet-Lagreze, E. & Siskos, J., 1982. "Assessing a set of additive utility functions for multicriteria decision-making, the UTA method," European Journal of Operational Research, Elsevier, vol. 10(2), pages 151-164, June.
    11. Liu, Jiapeng & Wang, Yan & Kadziński, Miłosz & Mao, Xiaoxin & Rao, Yuan, 2024. "A multiple criteria Bayesian hierarchical model for analyzing heterogeneous consumer preferences," Omega, Elsevier, vol. 128(C).
    12. Martyn, Krzysztof & Kadziński, Miłosz, 2023. "Deep preference learning for multiple criteria decision analysis," European Journal of Operational Research, Elsevier, vol. 305(2), pages 781-805.
    13. Wu, Xingli & Liao, Huchang, 2023. "A compensatory value function for modeling risk tolerance and criteria interactions in preference disaggregation," Omega, Elsevier, vol. 117(C).
    14. Xinyu Zhang & Yanyuan Ma & Raymond J. Carroll, 2019. "MALMEM: model averaging in linear measurement error models," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 81(4), pages 763-779, September.
    15. Sen, Sahana (Shahana) & Gorgoglione, Michele & Panniello, Umberto, 2025. "The Influence of the Perceived Hedonic vs. Utilitarian Product Type on Consumers’ Brand Engagement on Social TV," Journal of Business Research, Elsevier, vol. 196(C).
    16. Jindong Qin & Pan Zheng & Xiaojun Wang, 2024. "Product Redesign and Innovation Based on Online Reviews: A Multistage Combined Search Method," INFORMS Journal on Computing, INFORMS, vol. 36(3), pages 742-765, May.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Yu Yang & Yelin Fu & Siying Chen, 2026. "Group Preference Construction with Attitudinal Consensus Building Based on Uncertain Preference Disaggregation Analysis," Group Decision and Negotiation, Springer, vol. 35(2), pages 1-31, June.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Wu, Xingli & Liao, Huchang, 2025. "Determining investment allocation strategies to improve consumer satisfaction based on a preference learning model," Journal of Retailing and Consumer Services, Elsevier, vol. 82(C).
    2. Wu, Xingli & Zhu, Ting, 2025. "From data to diagnosis: A logical learning method to enhance interpretability in bipolar and major depressive disorder identification," European Journal of Operational Research, Elsevier, vol. 325(2), pages 362-380.
    3. Liu, Xiao & Li, Ming-Yang & Yuan, Duo-Ning, 2026. "Analyzing consumer satisfaction using Interpretive Structural Modeling driven by online reviews: An integrated approach," Journal of Business Research, Elsevier, vol. 205(C).
    4. Zhou, Kun & Gong, Zaiwu & Wei, Guo & Słowiński, Roman, 2025. "Preference disaggregation analysis with criteria selection in a regularization framework," Omega, Elsevier, vol. 133(C).
    5. Kim, Su-Ah & Park, Sohyun & Kwak, Minjung & Kang, Changmuk, 2025. "Examining product quality and competitiveness via online reviews: An integrated approach of importance performance competitor analysis and Kano model," Journal of Retailing and Consumer Services, Elsevier, vol. 82(C).
    6. Grillo, Marco & Kotłowski, Wojciech & Kadziński, Miłosz, 2025. "Ordinal regression meets online learning: Interactive preference learning for multiple criteria choice and ranking with provable guarantees," European Journal of Operational Research, Elsevier, vol. 327(3), pages 1003-1022.
    7. Li, Zhuolin & Zhang, Zhen & Pedrycz, Witold, 2025. "An incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting," European Journal of Operational Research, Elsevier, vol. 323(2), pages 553-570.
    8. Li, Zhuolin & Zhang, Zhen & Pedrycz, Witold, 2025. "Integrating machine learning models to learn potentially non-monotonic preferences for multi-criteria sorting from large-scale assignment examples," Omega, Elsevier, vol. 131(C).
    9. Wu, Xingli & Liao, Huchang, 2023. "A compensatory value function for modeling risk tolerance and criteria interactions in preference disaggregation," Omega, Elsevier, vol. 117(C).
    10. Wu, Xingli & Liao, Huchang, 2023. "Value-driven preference disaggregation analysis for uncertain preference information," Omega, Elsevier, vol. 115(C).
    11. Seiti, Hamidreza & Shabani, Mostafa & Ghanbari, Hossein & Ben-Amor, Sarah & Hameed, Ibrahim A., 2026. "Novel causal decision models for human-centric virtual reality platform selection in supply chain risk management," Omega, Elsevier, vol. 140(C).
    12. Li, Yijun & Guo, Mengzhuo & Kadziński, Miłosz & Zhang, Qingpeng & Xu, Chenxi, 2025. "Data-driven preference learning methods for sorting problems with multiple temporal criteria," European Journal of Operational Research, Elsevier, vol. 323(3), pages 918-937.
    13. Wen, Zhi & Liao, Huchang & Figueira, José Rui, 2024. "A preference disaggregation-driven multiple criteria sorting model based on regret theory," Omega, Elsevier, vol. 129(C).
    14. Wang, Binni & Wang, Pong & Tu, Yiliu, 2021. "Customer satisfaction service match and service quality-based blockchain cloud manufacturing," International Journal of Production Economics, Elsevier, vol. 240(C).
    15. Kadziński, MiŁosz & Greco, Salvatore & SŁowiński, Roman, 2012. "Extreme ranking analysis in robust ordinal regression," Omega, Elsevier, vol. 40(4), pages 488-501.
    16. Reinhold Decker, 2014. "Real-Time Analysis of Online Product Reviews by Means of Multi-Layer Feed-Forward Neural Networks," International Journal of Business and Social Research, MIR Center for Socio-Economic Research, vol. 4(11), pages 60-70, November.
    17. Tingting Song & Jinghua Huang & Yong Tan & Yifan Yu, 2019. "Using User- and Marketer-Generated Content for Box Office Revenue Prediction: Differences Between Microblogging and Third-Party Platforms," Service Science, INFORMS, vol. 30(1), pages 191-203, March.
    18. Cao, Jingcun & Li, Xiaolin & Zhang, Lingling, 2025. "Is relevancy everything? A deep-learning approach to understand the effect of image-text congruence," LSE Research Online Documents on Economics 128215, London School of Economics and Political Science, LSE Library.
    19. Pradeep Kumar Ponnamma Divakaran & Jie Xiong, 2022. "Eliciting brand association networks: A new method using online community data," Post-Print hal-03700393, HAL.
    20. Kadziński, Miłosz & Wójcik, Michał & Ciomek, Krzysztof, 2022. "Review and experimental comparison of ranking and choice procedures for constructing a univocal recommendation in a preference disaggregation setting," Omega, Elsevier, vol. 113(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:jbrese:v:201:y:2025:i:c:s0148296325005648. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/jbusres .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.