Combined Text-Mining/DEA method for measuring level of customer satisfaction from online reviews

Determining the best way to measure level of customer satisfaction (LCS) with service quality and its determinants has been a matter of concern for both practitioners and researchers. This is especially so, as LCS can be used to retain customers, sell products and services, improve the quality and value of offers and ensure more efficient and economical operating. The present study proposes a new LCS evaluation methodology that combines data envelopment analysis (DEA) with text mining to analyze online textual reviews. The proposed methodology identifies, from online reviews using a term-frequency-inverse document frequency (TF-IDF) algorithm, multiple satisfaction metrics that significantly affect customers' service experience, quantifies them by sentiment analysis, and evaluates, by a DEA model, service providers' LCS with respect to those metrics. To illustrate the efficacy and applicability of the proposed approach, an empirical case study applying it to the world's top 20 airlines in 2020 was conducted. This study demonstrates how the DEA model can be effectively utilized for evaluation of LCS from online textual review data by combining it with the TF-IDF text-mining technique.

Automated summary

Determining how to measure customer satisfaction with service quality and its determinants is a concern for practitioners and researchers. This study proposes a new methodology that combines data envelopment analysis (DEA) with text mining to analyze online textual reviews. The methodology identifies satisfaction metrics from online reviews using a TF-IDF algorithm, quantifies them by sentiment analysis, and evaluates service providers' LCS using a DEA model. An empirical case study applying this approach to the world's top 20 airlines in 2020 demonstrates its effectiveness.