Extracting Factors through Additional Impression Evaluation Experiment Assessing Both High-rated and Low-rated Reviews Posted at EC Sites

Authors

  • Yuya Yokoyama Advanced Institute of Industrial Technology
  • Takaaki Hosoda Advanced Institute of Industrial Technology
  • Tokuro Matsuo Advanced Institute of Industrial Technology

DOI:

https://doi.org/10.52731/liir.v006.336

Keywords:

EC site, Factor analysis, Factor loading, High-rated Review, Impression evaluation experiment, Impression word

Abstract

The global diffusion Internet has established electronic commerce (EC) sites where anyone can purchase online. In order to avoid a mismatch between user and products, users can write a review on the product they purchased, helping users refer to the review of the commodity and make decisions. Nevertheless, with more users and items flooded on EC sites, the issues of mismatches are becoming conspicuous. In order to solve these issues, the authors conducted impression evaluation experiment to extract the impression of low-rated reviews. However, the previous analysis yielded only three factors due to insufficient experimental materials. Therefore, this paper reports further experiment with appending high-rated reviews. As a result of the analysis, eight factors are obtained under the fifty impression words. It could be concluded that the approach of extracting impression from the statements can be applicable to the review statements of EC sites under the unbiased experimental materials.

References

Results of FY2022 E-Commerce Market Survey Compiled (URL, in Japanese), - Ministry of Economy, Trade and Industry, https://www.meti.go.jp/press/2023/08/20230831002/ 20230831002.html, 2025-01-10.

Rakuten Ichiba (URL, in Japanese), https://www.rakuten.co.jp, 2025-01-10.

Amazon (URL), https://www.amazon.com, 2025-01-10.

D. Li, H. Nishikawa, M. Ueda, and S. Nakajima, “A Store Evaluation System using AutomaticScoring of Retail Stores Based on Product Review Analysis”, Proc. of the 2023 IEEE Interna-tional Conference on Big Data (BigData), pp.2124-2130, 2023.

M Yoshida, T Tabata and T Hosoda, “A Study on Relationship Between Consumer Review Be-havior and Purchasing in EC site,” Proc. of the 9th International Congress on Advanced AppliedInformatics (AAI 2020), pp.791-796, 2020.

K. Horie, M. Onoda and T. Kaneko, “A proposal of review extraction method considering theknowledge amount of consumers and the purchase stage,” Total Quality Science, Vol.4, No.2,pp.83-91. 2018.

Y. Yokoyama, T. Hochin, H. Nomiya and T. Satoh, “Obtaining Factors Describing Impression ofQuestions and Answers and Estimation of their Scores from Feature Values of Statements,”Software and Network Engineering, Springer, Volume 413, pp.1-13, 2013.

Y. Yokoyama, T. Hochin and H. Nomiya, “Estimation of Factor Scores from Feature Values ofEnglish Question and Answer Statements,” Proc. of IEEE/ACIS 15th International Conferenceon Computer and Information Science (ICIS 2016), pp.741-746, 2016.

Y. Yokoyama, T. Hosoda and T. Matsuo, “Extracting Impression from the Low-Rated StatementsPosted at EC Sites,” Proc. of the 16th International Congress on Advanced Applied Informatics(AAI 2024), pp.9-14, 2024.

Rakuten Group, Inc. (2020): Rakuten Ichiba data. Informatics Research Data Repository, Na-tional Institute of Informatics. (dataset). (URL), https://doi.org/10.32130/idr.2.1, 2025-01-10.

Rakuten Data Release (URL), https://rit.rakuten.com/data_release/, 2025-01-10.

Downloads

Published

2025-02-22