Effects of user similarity in social media

  • Authors:

  • Ashton Anderson;Daniel Huttenlocher;Jon Kleinberg;Jure Leskovec

  • Affiliations:

  • Stanford University, Stanford, CA, USA;Cornell University, Ithaca, NY, USA;Cornell University, Ithaca, NY, USA;Stanford University, Stanford, CA, USA

  • Venue:
  • Proceedings of the fifth ACM international conference on Web search and data mining
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

There are many settings in which users of a social media application provide evaluations of one another. In a variety of domains, mechanisms for evaluation allow one user to say whether he or she trusts another user, or likes the content they produced, or wants to confer special levels of authority or responsibility on them. Earlier work has studied how the relative status between two users - that is, their comparative levels of status in the group - affects the types of evaluations that one user gives to another. Here we study how similarity in the characteristics of two users can affect the evaluation one user provides of another. We analyze this issue under a range of natural similarity measures, showing how the interaction of similarity and status can produce strong effects. Among other consequences, we find that evaluations are less status-driven when users are more similar to each other; and we use effects based on similarity to provide a plausible mechanism for a complex phenomenon observed in studies of user evaluation, that evaluations are particularly low among users of roughly equal status. Our work has natural applications to the prediction of evaluation outcomes based on user characteristics, and the use of similarity information makes possible a novel application that we introduce here - to estimate the chance of a favorable overall evaluation from a group knowing only the attributes of the group's members, but not their expressed opinions.