دانلود رایگان مقاله انگلیسی اهمیت نسبی ابعاد کیفیت خدمات در تجارب تجارت الکترونیک - الزویر 2018

ABSTRACT

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).

7. Limitations and conclusions

As with any study of this nature we acknowledge some limitations. While our findings provide useful insights, they are affected by the selection of the service quality model. In the future, researchers can focus on expanding upon our work by comparing multiple service quality models in order to assess the one that is more capable of accurately capturing the topics affecting customers’ evaluation. Moreover, we only extracted topics representing the SERVQUAL dimensions. So, another extension would be to control other aspects that can impact the overall customer experience (price, product quality etc.). Furthermore, our dataset includes only review in Italian related to Italian merchants. We plan to use the same methodology on datasets that contain English reviews about international merchants to improve the generalizability of the study. Despite the above limitations, our exploratory study contributes to research on the use of the increasing wealth of digitally streamed data. Our results should also prove useful to designers and users of customer service systems. We believe that an organization that exploits social data spontaneously generated by their customers not only can improve service quality measurement, but also can have a better understanding of the aspects that influence their satisfaction expressed as an overall rating. In fact, the average of ratings, given their distribution in online reviews, can not be considered a reliable measure (Hu et al., 2006) and even a neutral rating is not always representative of a neutral opinion (Jabr & Zheng, 2013). Moreover, in this way it will be possible to make decisions based on information gathered directly from their customers and avoid the current behavior of following what other companies do (Ostrom et al., 2015). An effective measurement of service quality must be based on customer experience (Petter et al., 2012). Furthermore, service quality evaluation systems should be able to map with reviews’ topic content in order to improve customer experience and to increase measurement accuracy. Companies that want to achieve high customer service cannot ignore topics that effectively and heavily affect their evaluation.