The relative importance of service quality dimensions in E-commerce experiences

Purpose: The proliferation of socialized data offers an unprecedented opportunity for customer service measurement. This paper addresses the problem of adequately measuring service quality using socialized data. Design/methodology/approach: The theoretical basis for the study is the widely used SERVQUAL model and we leverage a dataset uniquely suited for the analysis: the full database of online reviews generated on the website of the leading price comparison engine in Italy. Adopting a weakly supervised topic model, we extract the dimensions of service quality from these reviews. We use a linear regression to compare service quality dimensions between positive and negative opinions. Findings: First, we show that socialized textual data, not just quantitative ratings, provide a wealth of customer service information that can be used to measure service quality. Second, we demonstrate that the distribution of topics in online opinions differs significantly between positive and negative reviews. Specifically, we find that concerns about merchant responsiveness dominate negative reviews. Practical implications: Our research has important implications for designers of online review systems and marketers seeking novel approaches to the measurement of service quality. Our study shows that evaluation systems designed considering the knowledge extracted directly from customers' review lead to a service quality measurement that not only is theory-based, but also more accurate. Originality/value: We believe this is the first study to combine the advanced text mining technique of topic modeling and SERVQUAL to extract specific service dimensions from socialized data. Using these advanced techniques, we point to systematic differences between positive and negative customer opinions. We are not aware of any study that has shown these differences with either traditional approaches (i.e., survey data) or modern techniques (e.g. text mining).