Review-based measurement of customer satisfaction in mobile service: Sentiment analysis and VIKOR approach

Abstract

With the rapid growth and dissemination of mobile services, enhancement of customer satisfaction has emerged as a core issue. Customer reviews are recognized as fruitful information sources for monitoring and enhancing customer satisfaction levels, particularly as they convey the real voices of actual customers expressing relatively unambiguous opinions. As a methodological means of customer review analysis, sentiment analysis has come to the fore. Although several sentiment analysis approaches have proposed extraction of the emotional information from customer reviews, however, a lacuna remains as to how to effectively analyze customer reviews for the purpose of monitoring customer satisfaction with mobile services. In response, the present study developed a new framework for measurement of customer satisfaction for mobile services by combining VIKOR (in Serbian: ViseKriterijumsa Optimizacija I Kompromisno Resenje) and sentiment analysis. With VIKOR, which is a compromise ranking method of the multicriteria decision making (MCDM) approach, customer satisfaction for mobile services can be accurately measured by a sentiment-analysis scheme that simultaneously considers maximum group utility and individual regret. The suggested framework consists mainly of two stages: data collection and preprocessing, and measurement of customer satisfaction. In the first, data collection and preprocessing stage, text mining is utilized to compile customer-review-based dictionaries of attributes and sentiment words. Then, using sentiment analysis, sentiment scores for attributes are calculated for each mobile service. In the second stage, levels of customer satisfaction are measured using VIKOR. For the purpose of illustration, an empirical case study was conducted on customer reviews of mobile application services. We believe that the proposed customer-review-based approach not only saves time and effort in measuring customer satisfaction, but also captures the real voices of customers.