Predicting review helpfulness in an online clothing shopping mall
ZiYi Wang1 · Seunga Jung2 · Seongbeom Lim3 · Hanjun Lee4
1234Department of Management Information Systems, Myongji University
Correspondence to: 1 Ph. D. student, Departmet of Management Information Systems, Myongji University, Seoul 03674, Korea.
2 Student, Departmet of Management Information Systems, Myongji University, Seoul 03674, Korea.
3 Student, Departmet of Management Information Systems, Myongji University, Seoul 03674, Korea.
4 Corresponding author: Associate professor, Department of Management Information Systems, Myongji University, Seoul 03674, Korea. E-mail: hjlee1609@gmail.com
2 Student, Departmet of Management Information Systems, Myongji University, Seoul 03674, Korea.
3 Student, Departmet of Management Information Systems, Myongji University, Seoul 03674, Korea.
4 Corresponding author: Associate professor, Department of Management Information Systems, Myongji University, Seoul 03674, Korea. E-mail: hjlee1609@gmail.com
Received August 7, 2024; Revised October 4, 2024; Accepted October 10, 2024.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Abstract
- A common problem in online shopping malls is that too many reviews interfere with consumers’ purchase decisions, and various studies have been conducted to solve this problem. In this study, we propose a model to predict the helpfulness of reviews by utilizing reviewers’ physical information and information in reviews provided by online clothing shopping malls. To this end, we collected 78,040 reviews from Musinsa, a Korean clothing shopping mall, and built machine learning-based review helpfulness prediction models by utilizing product and reviewer information, including reviewers’ body shape information and information in the review text. Among them, the random forest model showed the best prediction performance with an accuracy of about 91 percent, and the feature importance and SHAP analysis confirmed the influence of reviewers’ physical information and information in reviews on the prediction of review helpfulness.
- Keywords : Machine learning, Musinsa, online review, random forest, review helpfulness
Full Text(PDF) Free
