Are We Who We Follow? Analyzing Human Personality and Brand Following on Twitter

• In Event: Semantics and Structure of Online Communication

Abstract

This study presents a computational method for analyzing the congruence between personality of brand’s Twitter accounts and the personality of their followers. By studying three very different types of brands, results revealed support that on average, Twitter followers of brands have personalities that are more congruent with the personality of brands they follow compared to users that do not follow those brands. As far as we know, this is the first study to investigate attachment to brands on Twitter by computing personalities through a computational analysis of Twitter postings rather than personality tests. Additionally, most studies utilizing Twitter data are limited by Twitter’s API sampling, but this study works with full data for each Twitter user, further contributing to the accuracy of personality dimensions. We will discuss implications of the findings for researchers and practitioners as well as include information for other researchers to use the method for future work.

Authors

• Joseph T Yun, U of Illinois Urbana Champaign

• Utku Pamuksuz, U of Illinois - Urbana-Champaign

• Brittany R. L. Duff, U of Illinois at Urbana-Champaign