Mining micro-influencers from social media posts

Abstract

Micro-influencers have triggered the interest of commercial brands, public administrations, and other stakeholders because of their demonstrated capability of sensitizing people within their close reach. However, due to their lower visibility in social media platforms, they are challenging to be identified. This work proposes an approach to automatically detect micro-influencers and to highlight their personality traits and community values by computationally analyzing their writings. We introduce two learning methods to retrieve Five Factor Model and Basic Human Values scores. These scores are then used as feature vectors of a Support Vector Machines classifier. We define a set of rules to create a micro-influencer gold standard dataset of more than two million tweets and we compare our approach with three baseline classifiers. The experimental results favor recall meaning that the approach is inclusive in the identification.