A Machine Learning Approach to Analyze Fashion Styles from Large Collections of Online Customer Reviews

2021 6th International Conference on Business and Industrial Research (ICBIR) Pub Date : 2021-05-20 DOI:10.1109/ICBIR52339.2021.9465830

Valentinus Roby Hananto, Soomin Kim, Máté Kovács, U. Serdült, V. Kryssanov

{"title":"A Machine Learning Approach to Analyze Fashion Styles from Large Collections of Online Customer Reviews","authors":"Valentinus Roby Hananto, Soomin Kim, Máté Kovács, U. Serdült, V. Kryssanov","doi":"10.1109/ICBIR52339.2021.9465830","DOIUrl":null,"url":null,"abstract":"Social media and online reviews have changed customer behavior when buying fashion products online. Online customer reviews also provide opportunities for businesses to deliver improved customer experiences. This study aims to develop fashion style models, based on online customer reviews from e-commerce systems to analyze customer preferences. Topic Modeling with Latent Dirichlet Allocation (LDA) was performed on a large collection of online customer reviews in different categories to investigate customer preferences by building fashion style models in a semantic space. Online product review data from Amazon, one of the leading online shopping websites globally, and Rakuten, one of the representative online shopping websites in Japan, were used to reveal the hidden topics in the review texts. The obtained topic definitions were manually examined, and the results were used to build computational models reflecting semantic relationships. The obtained fashion style models can potentially help marketing and product design specialists better understand customer preferences in the e-commerce fashion industry.","PeriodicalId":447560,"journal":{"name":"2021 6th International Conference on Business and Industrial Research (ICBIR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 6th International Conference on Business and Industrial Research (ICBIR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICBIR52339.2021.9465830","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

Abstract

Social media and online reviews have changed customer behavior when buying fashion products online. Online customer reviews also provide opportunities for businesses to deliver improved customer experiences. This study aims to develop fashion style models, based on online customer reviews from e-commerce systems to analyze customer preferences. Topic Modeling with Latent Dirichlet Allocation (LDA) was performed on a large collection of online customer reviews in different categories to investigate customer preferences by building fashion style models in a semantic space. Online product review data from Amazon, one of the leading online shopping websites globally, and Rakuten, one of the representative online shopping websites in Japan, were used to reveal the hidden topics in the review texts. The obtained topic definitions were manually examined, and the results were used to build computational models reflecting semantic relationships. The obtained fashion style models can potentially help marketing and product design specialists better understand customer preferences in the e-commerce fashion industry.

查看原文本刊更多论文

从大量在线客户评论中分析时尚风格的机器学习方法

社交媒体和在线评论已经改变了消费者在线购买时尚产品的行为。在线客户评论也为企业提供了改善客户体验的机会。本研究旨在开发时尚风格模型，基于电子商务系统的在线客户评论来分析客户偏好。利用潜在狄利克雷分配(Latent Dirichlet Allocation, LDA)对大量不同类别的在线顾客评论进行主题建模，通过在语义空间中建立时尚风格模型来研究顾客偏好。利用全球领先的在线购物网站之一亚马逊和日本代表性的在线购物网站之一乐天的在线产品评论数据，揭示评论文本中隐藏的主题。人工检查获得的主题定义，并使用结果构建反映语义关系的计算模型。获得的时尚风格模型可以潜在地帮助营销和产品设计专家更好地了解电子商务时尚行业中的客户偏好。

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

2021 6th International Conference on Business and Industrial Research (ICBIR)

自引率

0.00%

发文量