Uncovering Influence Cookbooks : Reverse Engineering the Topological Impact in Peer Ranking Services - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Uncovering Influence Cookbooks : Reverse Engineering the Topological Impact in Peer Ranking Services

Résumé

Ensuring the early detection of important social network users is a challenging task. Some peer ranking services are now well established, such as PeerIndex, Klout, or Kred. Their function is to rank users according to their influence. This notion of influence is however abstract, and the algorithms achieving this ranking are opaque. Following the rising demand for a more transparent web, we explore the problem of gaining knowledge by reverse engineering such peer ranking services, with regards to the social network topology they get as an input. Since these services exploit the online activity of users (and therefore their connectivity in social networks), we provide a method allowing a precise evaluation of the extent to which given topological metrics regarding the social network are involved in the assessment of the final user ranking. Our approach is the following : we first model the ranking service as a black-box with which we interact by creating user profiles and by performing operations on them. Through those profiles, we trigger some slight topological modifications. By monitoring the impact of these modifications on the rankings of created users, we infer the weight of each topo-logical metric in the black-box, thus reversing the service influence cookbook.
Fichier principal
Vignette du fichier
cscw16.pdf (168.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01644568 , version 1 (22-11-2017)

Identifiants

  • HAL Id : hal-01644568 , version 1

Citer

Erwan Le Merrer, Gilles Trédan. Uncovering Influence Cookbooks : Reverse Engineering the Topological Impact in Peer Ranking Services. 20th ACM Conference on Computer-Supported Cooperative Work and Social Computing CSCW 2017, Feb 2017, Portland, United States. 5p. ⟨hal-01644568⟩
67 Consultations
74 Téléchargements

Partager

Gmail Facebook X LinkedIn More