Customer satisfaction assessment model based on online reviews using principal component analysis

The relevance of the study is due to the high popularity of Internet services for publishing reviews of goods / services, their impact on consumer behavior, as well as the need to automate the processing of data from such services due to the large amount of information provided. A model for assessing customer satisfaction based on their feedback has been developed, taking into account the assessment of the product by the consumer, which determines the nature of the response (negative, positive, neutral), and the assessment of the feedback by other participants. The integral indicator of satisfaction assessment is formed based on normalized values of the average assessment of consumers and the total assessments of positive, neutral and negative reviews. In this case, the determination of the weight coefficients used in the calculation of the integral indicator was carried out using the method of principal components. The article presents the results of calculating the integral indicator for six models of video cards. Based on the developed model, a program has been implemented that allows automating the collection of data from the Internet site and calculating the integral indicator. The program is implemented using the Java programming language and the IntelliJ IDEA development environment. The developed model and program can be used both by potential buyers who make a decision to purchase goods, and by enterprises selling goods, and seeking to get feedback, identify weak and strong points, improve the range and quality of service.

1. Gribanova Е.B., Savitsky А.S. Development of a program to estimate the time of posting a message in the online social network VKontakte. Modeling, Optimization and Information Technology. 2020. Available at: https://moitvivt.ru/ru/journal/article?id=724. DOI: 10.26102/2310-6018/2020.28.1.012 (In Russ) (accessed: 25.02.2021).

2. Ghose A., Ipeirotis P. Designing Ranking Systems for Consumer Re-views: The Impact of Review Subjectivity on Product Sales and Review Quality. Proceedings of the 16th annual workshop on information technology and systems. 2006:303-310.

3. Ho-Dac N.N., Carson S.J., Moore W.L. The Effects of Positive and Negative Online Customer Reviews: Do Brand Strength and Category Maturity Matter? Journal of Marketing. 2013:37-53.

4. Zhao H., Jiang L., Su C. To Defend or Not to Defend? How Re-sponses to Negative Customer Review Affect Prospective customers' Distrust and Purchase Intention. Journal of Interactive Marketing. 2020:45-64.

5. Zhao K., Stylianou A.C., Zheng Y. Sources and Impacts of Social Influence from Online Anonymous User Reviews. Information and Management. 2018:16-30.

6. Gafni R., Gola O.T. The Influence of Negative Consumer Reviews in Social Networks. Online Journal of Applied Knowledge Management. 2016:44-58.

7. Mohammadiani R.P., Mohammadi S., Malik Z. Understanding the relationship strengths in users' activities, review helpfulness and influence. Computers in Human Behavior. 2017:117–129.

8. Xing S., Liu F., Wang Q., Zhao X., Li T. A hierarchical attention model for rating prediction by leveraging user and product reviews. Neurocomputing. 2019:417–427.

9. Kendyukhov A.V., Tolkachev D.O. Ispol'zovanie metoda glavnykh komponent dlya otsenki konkurentosposobnosti mashinostroitel'nykh predpriyatii. Marketing і menedzhment іnnovatsіi. 2013:219–227.

10. Petroni A., Braglia M. Vendor Selection Using Principal Component Analysis. The Journal of Supply Chain Management. 2000:63–69.

11. Sarkodie S.A., Adom P.K. Determinants of energy consumption in Kenya: A NIPALS approach. Energy. 2018:696–705.