Development of a Quantification Method for Impressions of Apparel Products Using Review Texts
Open Access
- 1 January 2025
- journal article
- Published by Japan Society of Kansei Engineering in International Journal of Affective Engineering
- Vol. 25 (3) , 471-483
Abstract
In recent years, it has become necessary to establish methods for quantitatively evaluating human Kansei and impressions to meet the needs of consumers. In this study, a method for quantitatively evaluating impressions of apparel products using online reviews is proposed. Four impression scales (“Dark-Bright,” “Tight-Loose,” “Formal-Casual,” and “Simple-Fancy”) were defined, and an impression dictionary was constructed that includes impression words containing degree adverbs, extreme impression words, and negation words. Validation using large-scale data confirmed that negation words accurately captured impression polarity, while degree adverbs and extreme impression words reflected impression intensity. Statistical analysis showed that scales related to physical characteristics (such as color and fit) were sensitive to modifiers, whereas the Simple-Fancy scale remained stable. In the future, model accuracy will be further validated and the applicability of the method to other fields will be explored.Keywords
This publication has 15 references indexed in Scilit:
- A Visualization System for Assistance of Semi-Automated Annotation Tasks based on Impression EvaluationsThe Journal of the Society for Art and Science, 2022
- Implicit Aspect Extraction from Online Clothing Reviews with Fine-tuning BERT AlgorithmJournal of Physics: Conference Series, 2021
- Impression Estimation Model for Clothing Patterns Using Neural Style Features2020
- Topic Sentiment Analysis in Online Learning Community from College StudentsJournal of Data and Information Science, 2020
- Quantitative trend analysis of luxury fashion based on visual impressions of young Japanese womenInternational Journal of Fashion Design, Technology and Education, 2016
- Generic and specific impression estimation of clothing fabric images based on machine learning2015
- Adjectival extremeness: degree modification and contextually restricted scalesNatural Language & Linguistic Theory, 2012
- Lexicon-Based Methods for Sentiment AnalysisComputational Linguistics, 2011
- Review sentiment scoring via a parse-and-paraphrase paradigm2009
- Comparison of Two Different Methods for the Evaluation of Left Ventricular Ejection Fraction in Patients with Coronary Artery DiseaseAngiology, 2002