Mining Marketing Meaning from Online Chatter: Strategic Brand Analysis of Big Data Using Latent Dirichlet Allocation

Abstract

Online chatter, or user-generated content, constitutes an excellent emerging source for marketers to mine meaning at a high temporal frequency. This article posits that this meaning consists of extracting the key latent dimensions of consumer satisfaction with quality and ascertaining the valence, labels, validity, importance, dynamics, and heterogeneity of those dimensions. The authors propose a unified framework for this purpose using unsupervised latent Dirichlet allocation. The sample of user-generated content consists of rich data on product reviews across 15 firms in five markets over four years. The results suggest that a few dimensions with good face validity and external validity are enough to capture quality. Dynamic analysis enables marketers to track dimensions’ importance over time and allows for dynamic mapping of competitive brand positions on those dimensions over time. For vertically differentiated markets (e.g., mobile phones, computers), objective dimensions dominate and are similar across markets, heterogeneity is low across dimensions, and stability is high over time. For horizontally differentiated markets (e.g., shoes, toys), subjective dimensions dominate but vary across markets, heterogeneity is high across dimensions, and stability is low over time.