Finding Experts on Facebook Communities: Who Knows More?

Abstract

Online communities have become important places for users to share information. In this context, the work described in this article aims to analyze computational methods that could allow us to identify users with the highest expertise levels on a specific knowledge domain in an online community. In this study the authots extracted data from a Java discussion group from an online community-Facebook, captured some important information and represented the community as a graph. Then, the authors compared the Bow-tie structure of this community with the ones from the Web and from a forum that are described in the literature. In addition, the authors tested some graph metrics and algorithms in order to analyze if they could provide a method to find the experts in this online community. The results show that four of the tested metrics can indicate if a user is an expert or not.