A Network Analysis for Assessing Similarities between Micro-Influencers and Their Followers in Music

Current ranking methods of influencers in social media are purely quantitative. This paper explores a qualitative alternative based on social network analysis (SNA) relying upon the novel content similarity score (CSS) between an influencer and a follower. In this scope, an AI Natural Language Processing (NLP) and data scrapping techniques are leveraged for CSS computation, while the network visualization tool Gephi contributes to SNA. Music micro-influencers from Instagram are considered in this paper because of the lack of research on the topic. By seeing through the similarity perspective, we can identify groups of reflective and non-reflective followers, which along other findings, help to reveal fruitful opportunities for influencers and marketers.