Words, Emotions and Networks: Profiling social media users
Francesca Greco, Andrea Fronzetti Colladon, Alessandro PolliIn the era of big data, customers often reveal their personal opinions and feelings, about products and brands, on social media. Accessing this information can be extremely relevant for companies and brand managers. This study presents a new approach for the profiling of social media users and the identification of brand communities, based on the analysis of communication styles and social behaviors.
We use the Semantic Brand Score (SBS), to evaluate the importance of discourse topics and brand representations, also with respect to competitors. We combine this with the Emotional Text Mining (ETM) technique for the identification of consumer clusters and the categorization of lexical profiles. Lastly, through social network analysis (SNA) we measure social dynamics of each brand community.
We show the advantages of our approach by presenting a case study – where we analyze more than 50,000 Twitter messages, written in English, about a well-known sportswear brand. Through the ETM we detect five communities (fashionistas, geeks, merchants, seekers, and purchasing groups), each one with its own representation of the brand. We discuss differences in brand representations and social behaviors of people belonging to different communities.
Our study advances research on words and networks, offering a new approach for the profiling of social media users, the analysis of brand representations and the identification of brand communities. Our findings have important practical implications for companies and brand managers.