Recognition on Online Social Network by user's writing style

Rodrigo Augusto Igawa,Bruno Zarpelão,Alex Almeida,Sylvio Barbon Jr

doi:10.5753/isys.2015.291

Rodrigo Augusto Igawa, Bruno Zarpelão + Show 2 more

Open Access

https://doi.org/10.5753/isys.2015.291

Copy DOI

Abstract

Compromising legitimate accounts is the most popular way of disseminating fraudulent content in Online Social Networks (OSN). To address this issue, we propose an approach for recognition of compromised Twitter accounts based on Authorship Verification. Our solution can detect accounts that became compromised by analysing their user writing styles. This way, when an account content does not match its user writing style, we affirm that the account has been compromised, similar to Authorship Verification. Our approach follows the profile-based paradigm and uses N-grams as its kernel. Then, a threshold is found to represent the boundary of an account writing style. Experiments were performed using two subsampled datasets from Twitter. Experimental results showed the developed model is very suitable for compromised recognition of Online Social Networks accounts due to the capacity of recognizing user styles over 95% accuracy for both datasets.

Highlights

Online Social Networks (OSNs) are environments where people discuss and express thoughts and opinions about any subject [Zappavigna 2011]
Knowledge obtained from OSNs such as Twitter and Facebook has shown to be extremely valuable for marketing research companies, public opinion organisations, and other Text Mining purposes [Bahrainian and Dengel 2013, Yu 2012, Zhou et al 2014, Smailovic et al 2014, Mostafa 2013, Hsieh et al 2012]
Our approach is based on N-grams Authorship Verification (AV) and we focus on recognition of a user based on its writing style

Summary

Introduction

Online Social Networks (OSNs) are environments where people discuss and express thoughts and opinions about any subject [Zappavigna 2011]. OSNs represent a relevant resource of information and research in areas such as Customer Relationship Management (CRM) and Opinion Mining (OM). To address the problem of malicious activity on social networks, researchers have focused the detection of fake accounts (i.e., automatically created accounts for only spreading malicious content). 64-85, 2015 discriminate between fake and compromised accounts. Accounts can be compromised in many different ways, for example, by exploiting a cross-site scripting vulnerability or by using a phishing scam to steal the users credentials. Bots have been increasingly used to obtain credentials information for social networking sites on infected hosts [Egele et al 2013, Grier et al 2010]

Methods

Results

Conclusion