TSim: a system for discovering similar users on Twitter

Abstract

Lately, social networks have become a vital part of our lives. Among many different uses, most people use social networks to communicate and stay informed. Twitter, a microblogging site, is currently one of the most popular social network sites. Users follow different accounts such as friends, celebrities, or companies to get information through 280 character messages (or tweets). There are currently 1.3 billion registered users on Twitter with 330 million of them active users generating 500 million tweets daily [1]. Analyzing Twitter content has recently gained a lot of attention due to its popularity all over the world and the significance of its content in detecting patterns and inferring hidden information. A significant portion of analyzing Twitter content goes into analyzing the opinions and behavior of its users. Detecting similarity between users based on their produced content, behavior, interests, and activities is an important application of Twitter content analysis as could be seen in [2-4]. Detecting similarity could be used in profiling users for security, recruitment and social reasons. Governments could use it to identify persons who impose a threat to the security of their people by identifying one individual and finding others similar to her/him. Businesses could benefit from it in recruitment and target marketing by identifying candidate Twitter users and finding similar ones to them. Individuals could use it to find similar users to them or to others who they are interested in.

WITHDRAWN: Detection of Political Intent Through Analysis of Tweets and Homophily Elements

“…Unlike direct tweets, here the contacts and the com-munication elements of the users were examined, to deduce the chosen political party from similar users. The connections analyzed in our work are described below [62].…”

An extensive work on comparing sentiment patterns in twitter archives between two persons

“…This paper [9] identifies the similar users for the purpose of profiling users with respect to social and security purposes. Seven attributes are used to profile users such as retweets, favourite and common hash tags, common interest, profile similarly following and followers.…”

Comprehensive Analysis of Two Malicious Arabic-Language Twitter Campaigns

“…Creating unique content or running every single account separately to hide the similarity among the group would greatly increase the costs and time to administer these accounts; therefore, researchers have suggested several systems and strategies expose various types of malicious accounts at the campaign level. For instance, a study [14] proposed examining the social graph between users and pages to reveal Fake-Likes campaigns on Facebook, and several studies have used the synchronized behavior and timing of social spammers' fraud activities, fake Twitter followers, and malicious retweeter groups to expose their accounts on Twitter [15], [16], [17], [18], [19]. Besides, a variety of analysis studies have been carried out to understand the various aspects of social spammers.…”