Suppressing Deceitful Influence in Cites-or-Writes Social Networks

This paper presents a method for analysing influence in a class of social networks that can be viewed as consisting of messengers and messages. A messenger may either write a message or cite (e.g., re-tweet, repost, grade, or like) a message originally written by another messenger. We term such social networks as cites-or-writes networks. The free citability of messages may lead to collusion among a small set of messengers to gain unwarranted influence. We propose a mathematically rigorous method for inferring the influence of a messenger and the impact of her message. As a key feature, our method does not require any configurable parameters. It only uses a matrix of messenger-writes-message data and a matrix of messenger-cites-message data. Another key feature of our technique is the suppression of collusion; i.e., messengers who deliberately promote each other by preferential citations are automatically suppressed in their influence. We discuss several examples of social networks that follow the cites-or-writes model. We show that our technique is fast enough to do large-scale social network analysis, and present a sample analysis for a large network.

By: Adam Hackett, Shoukat Ali, Stephen Kirkland, Massimiliano Meneghin

Published in: RC25419 in 2013

LIMITED DISTRIBUTION NOTICE:

This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.

rc25419.pdf

Questions about this service can be mailed to reports@us.ibm.com .