Method for Analysing Information on Psychosomatic Issues Based on Service Recipient Dissatisfaction
DOI:
https://doi.org/10.4108/eetsis.10574Keywords:
Social Networking Service, Cosmetics, Consumer Dissatisfaction, text miningAbstract
Recently, the proliferation of social networking services has facilitated free sharing of opinions and complaints by consumers. For companies, such reviews are a valuable source of information for product and service evaluation, and for identifying areas for improvement. In this investigation, the cosmetics industry was used as a case study for this phenomenon. Content related to ‘skin’ was extracted from consumer review information and related physical and mental problems were analysed. Specifically, a polarity dictionary specialized for cosmetics was built, and related reviews were extracted by identifying expressions of dissatisfaction related to the skin, such as ‘itchiness’, ‘redness’, and ‘dryness’. By classifying and analysing problem types, this analysis revealed the trends in consumer dissatisfaction and related issues, discovering insights useful for improving services and products. Therefore, the present study identified the types and causes of problems in providing practical knowledge that contributes to enhanced consumer satisfaction, reduced product risk, and effective marketing strategies.
References
[1] NTT Resonant Corporation: Survey on the influence of word of mouth on purchasing behaviour, https://research.nttcoms.com/database/data/001436/, last accessed 2025/06/10
[2] NORM Inc.: Thinking from the perspective of women's marketing: “Purchasing psychology influenced by UGC,” https://norm.co.jp/column/ugc, last accessed 2025/6/10
[3] Nikkei Research Inc.: Text mining. Glossary of survey and statistics terms, https://service.nikkei-r.co.jp/glossary/text-mining, last accessed 2025/06/10
[4] Higuchi, K.: Quantitative text analysis for social surveys - aiming for the inheritance and development of content analysis. 2nd edn. Nakanishiya Shuppan co. ltd, Japan, 2020
[5] Ohsumi, N., and Yasuda, A.: Reviewing Textual Data Mining in Japan. Sociological Theory and Methods 19(2), 135–159, 2004
[6] Etchu, K., Takada, Y., Kinoshita, H., Ando, A., Takahashi, K., Tabata, K., Oka, M., and Ishizawa, K.: An analysis of class evaluation questionnaires using text mining: an attempt to visualize free descriptions with a co-occurrence network. COMMUE 22, 67–74 , 2015
[7] Yui, K., Hata, R., Saotome, H., and Hoshino, Y.: Selective Consumer Use Among Review Sites – Case Study of Cosmetics in Japan -. In: Proceedings of the Japanese Society for Emotional Engineering 1(2), 951–953, 2024
[8] Anil, B., Nirmalie, W., Stewart, M., and Deepak, P.: Lexicon generation for emotion detection from text. IEEE Intelligent Systems 32(1), 102–108, 2017
[9] Saif, M. M.: Sentiment analysis: detecting valence, emotions, and other affectual states from text. In: Emotion Measurement, pp. 201–237, Elsevier B.V, Nederland, 2016
[10] Liu, B.: Sentiment analysis and opinion mining. Morgan & Claypool Publishers, America, 2012
[11] Yi, J., Nasukawa, T., Bunescu, R., and Niblack, W.: Sentiment analyzer: extracting sentiments about a given topic using natural language processing techniques. In: Third IEEE International Conference on Data Mining, pp. 427–434, IEEE, America, 2003
[12] Kanayama, H., and Nasukawa, T.: Extraction and organization of request expressions. In: Proceedings of the 11th Annual Meeting of the Association for Natural Language Processing, pp. 660–663, 2005
[13] Kobayashi, N., Inui, K., Matsumoto, U., Tateishi, K., and Fukushima, T.: Collecting evaluative expressions for opinion extraction. In: International Conference on Natural Language Processing, pp. 596–605. Springer, Berlin, 2004
[14] Higashiyama, M., Inui, K., and Matsumoto, Y.: Learning sentiment of nouns from selectional preferences of verbs and adjectives. In: Proceedings of the 14th Annual Meeting of the Association for Natural Language Processing, pp. 584–587, 2008
[15] Shah, P., Patel, H., and Swaminarayan, P.: Multitask Sentiment Analysis and Topic Classification Using BERT. In: EAI Endorsed Transactions on Scalable Information Systems Vol. 12 No. 1, pp. 1-12, 2025
[16] Kushwaha1, N., Singh, B., and Agrawal, S.: Manifesto of Deep Learning Architecture for Aspect Level Sentiment Analysis to extract customer criticism. In: EAI Endorsed Transactions on Scalable Information Systems Vol.11 No.6, pp. 1-15, 2024
[17] Takahashi, Y.: An empirical analysis of workers' physical and mental health using panel data: the problem of workers’ stress response from the perspective of labor economics. Journal of Economic Policy Studies 19(2), 1–16, 2022
[18] Senoo, M., Takemoto, Y., Iida, I., Sugaya, Y., and Jingū, H.: Emotional changes caused by the use of skincare formulations. Journal of the Society of Cosmetic Chemists of Japan 34(3), 267–272, 2000
[19] Baskaran, J., Sattar, U, M., and Khan, W, H.: Predicting product sales performance using various types of customer review data. In; EAI Endorsed Transactions on Scalable Information Systems Vol. 12 No. 4, pp. 1-11, 2025
[20] You, M., Ge, Y. F., Wang, K., Wang, H., Cao, J., and Kambourakis, G.: Hierarchical adaptive evolution framework for privacy-preserving data publishing. World Wide Web, 27(4), 49.
[21] Jahan, S., Ge, Y-F., Kabir, E., and Wang, H. In: Analysis and Multi-objective Protection of Public Medical Datasets from Privacy and Utility Perspectives. World Wide Web, 27(4), pp. 1-14.
[22] Khanam, T., Siuly, S., Wang, K., and Zheng, Z. A Privacy-Preserving Encryption Framework for Big Data Analysis
[23] Insight Tech, Inc.: Discontent Survey Dataset. National Institute of Informatics Research Data Repository (2017)
[24] Sueyoshi, M.: Introduction to text mining: data analysis with Excel and KH Coder. Ohmsha, Japan (2019)
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Maya Iwano, Yoshiyuki Kobayashi, Kakeru Ota, Kazuhiko Tsuda
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
