Service quality dimensions in Austrian food retailing – a text mining approach for physical retail stores

Abstract

Investigating Service Quality (SQ) and its implications for customer satisfaction has become an increasingly popular research area. Especially in the context of physical grocery retailing, ensuring customer satisfaction has become a key success factor. Most previous research studies apply traditional methods (e.g. surveys) for physical shops and utilize text mining-based approaches mainly for e-commerce. In our paper, we propose a novel approach based on LDA. By combining expert-based word counting analysis with the LDA approach, we confirm that unsupervised text mining based on LDA can be used as a reliable approach to cluster textual comments to SQ dimensions in physical retail settings. We have analyzed over 163,000 publicly available textual customer reviews related to the Austrian market, which is special in terms of its extremely high density of retail outlets, high price levels and a tendency towards traditional form of shopping. Our results show that personal interaction, policies, and product-related aspects seem to be positive drivers of customer satisfaction, while reliability is a clear driver of customer dissatisfaction. Results also show a significantly higher relevance of personal interaction in smaller stores and cities with fewer than 5,000 inhabitants than in other store types and bigger cities. Regarding practical implications, hypermarkets should focus on physical aspects to reduce negative reviews and increase efforts in personal interaction to increase positive reviews. On the other hand, smaller stores should continue to rely on personal interaction to avoid negative reviews and might focus on higher reliability to generate more positive reviews. The applied text-mining approach enables future research with a starting base to analyze SQ dimensions and their relevance in additional countries or area, as e.g. fashion or hardware retail.