R\^ole communautaire des capitalistes sociaux dans Twitter

TL;DR

This paper characterizes social capitalists on Twitter using a topological approach based on community roles, with modifications to existing measures and an objective detection method, revealing clear behavioral patterns.

Contribution

It introduces a new topological method for identifying community roles of social capitalists on Twitter, improving upon previous measures and providing an objective detection approach.

Findings

Identified roles are highly consistent with known social capitalist behavior.

Modified measures improve role detection accuracy.

Topological analysis effectively characterizes social capitalists without content analysis.

Abstract

Les capitalistes sociaux sont des utilisateurs de m\'edias sociaux tels que Twitter, appliquant diverses techniques pour obtenir un maximum de visibilit\'e. Ils peuvent \^etre n\'efastes \`a l'\'equilibre du service, dans la mesure o\`u leurs comptes, en gagnant en importance sans r\'eelle raison de contenu, rendent difficile l'acc\`es \`a un contenu pertinent. Dans ce travail, nous nous int\'eressons \`a leur caract\'erisation d'un point de vue purement topologique, i.e. sans consid\'erer la nature des contenus partag\'es. Nous utilisons pour cela la notion de r\^ole communautaire, qui est bas\'ee sur la structure de communaut\'es du r\'eseau \'etudi\'e. Nous apportons des modifications \`a des mesures pr\'ec\'edemment d\'efinies \`a cet effet, et proposons une m\'ethode objective de d\'etection des r\^oles. Nous appliquons ensuite notre m\'ethode \`a l'analyse d'un r\'eseau repr\'esentant Twitter. Nos r\'esultats montrent que les r\^oles que nous identifions via nos mesures se r\'ev\`elent particuli\`erement coh\'erents par rapport aux capitalistes sociaux du r\'eseau Twitter, dont le comportement est clairement identifi\'e---Social capitalists are social media users taking advantage of various methods to maximize their visibility. This results in artificially important accounts, in the sense this importance is not backed by any real content. The risk is then to see those accounts hiding relevant contents and therefore preventing other users to access them. In this work, we want to characterize social capitalists from a purely topological perspective, i.e. without considering the nature of the shared contents. For this purpose, we use the notion of community role, based on the community structure of the studied network. We modify some measures previously designed for this matter, and propose an objective method to determine roles. We then apply this method to the analysis of a Twitter network. Our results show the roles identified through our measures are particularly consistent with Twitter's social capitalists, whose behavior was clearly identified.