A product recommendation model based on online reviews: Improving PageRank algorithm considering attribute weights

IF 11 1区管理学 Q1 BUSINESS

Journal of Retailing and Consumer Services Pub Date : 2024-08-26 DOI:10.1016/j.jretconser.2024.104052

Xiaoli Wang, Chenxi Zhang, Zeshui Xu

{"title":"A product recommendation model based on online reviews: Improving PageRank algorithm considering attribute weights","authors":"Xiaoli Wang, Chenxi Zhang, Zeshui Xu","doi":"10.1016/j.jretconser.2024.104052","DOIUrl":null,"url":null,"abstract":"Consumer reviews play a crucial role in evaluating products on online e-commerce platforms. Unlike numerical ratings, online reviews provide valuable information and sentiment. However, existing studies often overlook the unique interrelationships between products on e-commerce platforms, and fail to adequately capture the psychological behavior of consumers during online shopping. To address these gaps, this study presents a novel product recommendation model based on online reviews that evaluates products’ multi-attribute performances. The study first identifies the product attributes that are most important to consumers by analyzing review texts. Then, this study calculates the attribute performance scores of each product by considering consumer sentiment and the usefulness of online reviews. Next, it identifies competitors for the target product using a weighted Euclidean distance function and ranks all products employing an improved PageRank algorithm. Finally, to illustrate the validity of the proposed model, the study conducts a case study using a dataset of 41,352 online reviews obtained from Best Buy, and segments the data into three categories according to price. Comparative results with traditional MCDM models show that among the three categories, our results achieved a maximum improvement of 18.3% in the Spearman correlation coefficient.","PeriodicalId":48399,"journal":{"name":"Journal of Retailing and Consumer Services","volume":"4 1","pages":""},"PeriodicalIF":11.0000,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Retailing and Consumer Services","FirstCategoryId":"91","ListUrlMain":"https://doi.org/10.1016/j.jretconser.2024.104052","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

Consumer reviews play a crucial role in evaluating products on online e-commerce platforms. Unlike numerical ratings, online reviews provide valuable information and sentiment. However, existing studies often overlook the unique interrelationships between products on e-commerce platforms, and fail to adequately capture the psychological behavior of consumers during online shopping. To address these gaps, this study presents a novel product recommendation model based on online reviews that evaluates products’ multi-attribute performances. The study first identifies the product attributes that are most important to consumers by analyzing review texts. Then, this study calculates the attribute performance scores of each product by considering consumer sentiment and the usefulness of online reviews. Next, it identifies competitors for the target product using a weighted Euclidean distance function and ranks all products employing an improved PageRank algorithm. Finally, to illustrate the validity of the proposed model, the study conducts a case study using a dataset of 41,352 online reviews obtained from Best Buy, and segments the data into three categories according to price. Comparative results with traditional MCDM models show that among the three categories, our results achieved a maximum improvement of 18.3% in the Spearman correlation coefficient.

查看原文本刊更多论文

基于在线评论的产品推荐模型：考虑属性权重改进 PageRank 算法

消费者评论在在线电子商务平台的产品评估中发挥着至关重要的作用。与数字评分不同，在线评论提供了有价值的信息和情感。然而，现有的研究往往忽视了电子商务平台上产品之间独特的相互关系，也未能充分捕捉到消费者在网上购物时的心理行为。针对这些不足，本研究提出了一种基于在线评论的新型产品推荐模型，该模型可评估产品的多属性表现。研究首先通过分析评论文本，确定对消费者最重要的产品属性。然后，本研究通过考虑消费者情感和在线评论的有用性，计算出每种产品的属性表现得分。接着，研究使用加权欧氏距离函数识别目标产品的竞争对手，并使用改进的 PageRank 算法对所有产品进行排名。最后，为了说明所提模型的有效性，本研究使用从百思买获得的 41,352 条在线评论数据集进行了案例研究，并根据价格将数据分为三类。与传统 MCDM 模型的比较结果表明，在三个类别中，我们的结果在斯皮尔曼相关系数方面取得了 18.3% 的最大改进。

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 Retailing and Consumer Services BUSINESS-

CiteScore

20.40

自引率

14.40%

发文量

340

审稿时长

20 days

期刊介绍： The Journal of Retailing and Consumer Services is a prominent publication that serves as a platform for international and interdisciplinary research and discussions in the constantly evolving fields of retailing and services studies. With a specific emphasis on consumer behavior and policy and managerial decisions, the journal aims to foster contributions from academics encompassing diverse disciplines. The primary areas covered by the journal are: Retailing and the sale of goods The provision of consumer services, including transportation, tourism, and leisure.