Home // International Journal On Advances in Intelligent Systems, volume 8, numbers 1 and 2, 2015 // View article
Authors:
Nafissa Yussupova
Maxim Boyko
Diana Bogdanova
Andreas Hilbert
Keywords: quality management; decision support system; sentiment analysis
Abstract:
This paper describes the application of a novel domain-independent decision support approach for Customer Satisfaction Research. It is based on customer satisfaction research through deep analysis of consumer reviews posted on the Internet in natural language. Artificial Intelligence techniques, such as web data extraction, sentiment analysis, aspect extraction, aspect-based sentiment analysis and data mining, are used for realization of consumer reviews analysis. In paper, specific Internet resources (such as yelp.com, tripadvisor.com, tophotels.ru) are used for accumulating customer reviews as a data source. This is performed in accordance with the quality standard ISO 10004 and proposed decision support approach, which allows for both qualitative and quantitative customer satisfaction surveys to be carried out. The output of the quantitative survey are values of customer satisfaction with product and each product’s aspect. The output of the qualitative survey are significance values of products aspect for customers and identified latent relations between overall satisfaction with product and satisfaction with products’ aspects. The proposed approach is performed as a prototype of a decision support system. To evaluate the efficacy of the proposed approach, two experiments on hotels and banks customer reviews have been carried out. The obtained results prove the efficacy of the proposed decision support approach for quality management and the concept of using it instead of classical methods of qualitative and quantitative research of customer satisfaction.
Pages: 145 to 158
Copyright: Copyright (c) to authors, 2015. Used with permission.
Publication date: June 30, 2015
Published in: journal
ISSN: 1942-2679