A review of features for the discrimination of twitter users: application to the prediction of offline influence

• Published in: Social network analysis and mining Vol. 6; no. 1; p. 25
• Main Authors: Cossu, Jean-Valère, Labatut, Vincent, Dugué, Nicolas
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.12.2016; Springer Nature B.V; Springer
• Subjects: Applications of Graph Theory and Complex Networks; Automation; Classification; Computation and Language; Computer Science; Data Mining and Knowledge Discovery; Diffusion of Information and Influence in Social Networks; Discrimination; Economics; Game Theory; Humanities; Law; Marketing; Methodology of the Social Sciences; Original Article; Quality of service; Social and Behav. Sciences; Social networks; Statistics for Social Sciences; Variants; Twitter; Influence; Natural language processing; Social network analysis; Social media; Complex networks
• ISSN: 1869-5450; 1869-5469
• DOI: 10.1007/s13278-016-0329-x

Many works related to Twitter aim at characterizing its users in some way: role on the service (spammers, bots, organizations, etc.), nature of the user (socio-professional category, age, etc.), topics of interest, and others. However, for a given user classification problem, it is very difficult to select a set of appropriate features, because the many features described in the literature are very heterogeneous, with name overlaps and collisions, and numerous very close variants. In this article, we review a wide range of such features. In order to present a clear state-of-the-art description, we unify their names, definitions and relationships, and we propose a new, neutral, typology. We then illustrate the interest of our review by applying a selection of these features to the offline influence detection problem. This task consists in identifying users who are influential in real life, based on their Twitter account and related data. We show that most features deemed efficient to predict online influence, such as the numbers of retweets and followers, are not relevant to this problem. However, we propose several content-based approaches to label Twitter users as influencers or not. We also rank them according to a predicted influence level. Our proposals are evaluated over the CLEF RepLab 2014 dataset, and outmatch state-of-the-art methods.