Segmenting an online reviewer community: Empirical detection and comparison of reviewer clusters

Abstract

Online review communities thrive on contributions from different reviewers, who exhibit a varying range of community behavior. However, no attempt has been made in the IS literature to cluster behavioral patterns across a reviewer population. In this paper, we segment the reviewers of a popular review site (Yelp) using two-step cluster analysis based on four key attributes (reviewer involvement, sociability, experience, and review quality), resulting in three distinct reviewer segments - Enthusiasts, Adepts, and Amateurs. We also compare the propensity of receiving community recognition across these segments. We find that the Enthusiasts, who show high involvement and sociability, are the most recognized. Surprisingly, the Adepts, who are high on review quality, are the least recognized. The study is a novel attempt on reviewer segmentation and provides valuable insights to the community managers to customize strategies to increase productivity of different segments. © ACIS 2017.