A preference learning method to estimate consumer preferences from online reviews

IF 9.8 1区管理学 Q1 BUSINESS

Journal of Business Research Pub Date : 2025-09-29 DOI:10.1016/j.jbusres.2025.115741

Xingli Wu, Huchang Liao

{"title":"A preference learning method to estimate consumer preferences from online reviews","authors":"Xingli Wu, Huchang Liao","doi":"10.1016/j.jbusres.2025.115741","DOIUrl":null,"url":null,"abstract":"<div><div>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.</div></div>","PeriodicalId":15123,"journal":{"name":"Journal of Business Research","volume":"201 ","pages":"Article 115741"},"PeriodicalIF":9.8000,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Business Research","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0148296325005648","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS","Score":null,"Total":0}

引用次数: 0

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.

查看原文本刊更多论文

一种从在线评论中估计消费者偏好的偏好学习方法

对消费者偏好的准确预测有助于电子商务平台上的许多营销工作，因为它可以确定哪些产品属性会产生影响，以及它们如何影响消费者的购买决策。本研究提出了一种偏好学习方法，用于从在线评论中自动提取消费者偏好。基于多属性价值理论，提出了一个消费者偏好模型来描述消费者的偏好结构。该模型连接了总体评级和属性级别的审查，同时结合了对属性重要性、属性之间的补偿效应和审查之间不一致的属性集的考虑。提出了一种基于优化模型的分类算法来估计偏好模型内的偏好参数。通过k-fold交叉验证来评估其预测精度，并通过仿真来衡量其鲁棒性。酒店、餐厅和汽车领域的案例研究验证了所提出的方法生成透明的偏好模型，具有稳健的预测性能和清晰的解释。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Business Research BUSINESS-

CiteScore

20.30

自引率

10.60%

发文量

956

期刊介绍： The Journal of Business Research aims to publish research that is rigorous, relevant, and potentially impactful. It examines a wide variety of business decision contexts, processes, and activities, developing insights that are meaningful for theory, practice, and/or society at large. The research is intended to generate meaningful debates in academia and practice, that are thought provoking and have the potential to make a difference to conceptual thinking and/or practice. The Journal is published for a broad range of stakeholders, including scholars, researchers, executives, and policy makers. It aids the application of its research to practical situations and theoretical findings to the reality of the business world as well as to society. The Journal is abstracted and indexed in several databases, including Social Sciences Citation Index, ANBAR, Current Contents, Management Contents, Management Literature in Brief, PsycINFO, Information Service, RePEc, Academic Journal Guide, ABI/Inform, INSPEC, etc.