Persona Generation from Aggregated Social Media Data


We develop a methodology for persona generation using real time social media data for the distribution of products via online platforms. From a large social media account containing more than 30 million interactions from users from 181 countries engaging with more than 4,200 digital products produced by a global media corporation, we demonstrate that our methodology can first identify both distinct and impactful user segments and then create persona descriptions by automatically adding pertinent features, such as names, photos, and personal attributes. We validate our approach by implementing the methodology into an actual working system that leverages large scale online user data for generation of persona descriptions. We present the overall methodological approach, data analysis process, and system development. Findings show this method can develop believable personas representing real groups of people using real-time online user data. Results have implications for those distributing products via online platforms.

Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI)