Modeling brand personality with business value of social media analytics: Predicting Brand Personality with User-generated Content and Firm-generated Content

Social media platforms have provided an enormous repository of textual data, which has brought about a grand opportunity in social media analytics, wherein valuable information can be extracted from content generated by consumers, employees, and firms. While research has shown the explicit value of social media in terms of its networking and campaign value, a growing literature is focused on extracting implicit valuable information embedded in the textual data. We showcase that firms can extract business intelligence from social media data with an important business application in measuring brand personality. Specifically, we develop a text analytics framework that integrates different distinct sources of social media data (consumer-generated content, employee-generated content, and firm-generated content) to measure brand personality. Based on Elastic-Net regression analysis of a large corpus of social media data, including self-descriptions of 1,996,214 consumers who followed the sample of brands, 312,400 employee reviews of the brands' firms, and 680,056 brand official tweets, further combining 10,950 consumer survey responses, we develop a brand personality model that achieves prediction accuracy as high as 0.78. We find that the profile of individuals who choose to associate with brands on social media is an important predictor of brand personality; this provides the first real-world evidence for the raison d'être of research into the brand personality construct, namely a consumer identity-brand personality link. We also identify a link between an organization's internal corporate environment and brand personality.