Investigating the effects of self presentation at social network sites on purchase behavior: A text mining and econometric approach

Abstract

With advances in information and communication technologies (ICT), companies and platforms look to use the increasing volume and diversity of user-generated content (UGC) to predict consumer behavior, but with mixed results. In this study, we propose a text mining technique to find support for self-presentation in online social media and show that this is correlated with the content producer's offline purchase behaviour. We use unique datasets from a social network site (SNS) and an offline fashion retailer to find that: 1) while public and private volume and sentiment metrics leads to nonsignificant predictions, the sentiment divergence can significantly explain offline purchases, 2) users who engage in SNS for self-presentation spend less money and buy less quantities, and 3) however, they spend more when exposed to specific site features that inspire self-presentation, like brand pages. Marketers and platform owners can benefit from our results by designing appropriate features to target such users.