Writer Identification Using Microblogging Texts for Social Media Forensics

TL;DR

This paper investigates authorship identification of Twitter messages using stylometric and platform-specific features, demonstrating high accuracy with sufficient training data and offering insights into feature effectiveness and computational aspects.

Contribution

It introduces a comprehensive evaluation of stylometric and Twitter-specific features for authorship attribution on short texts, with automatic feature selection and analysis of performance across different data sizes.

Findings

High accuracy (>80% Rank-5) with over 500 training Tweets and few test Tweets.

Reduced candidate search space by 9-15% with small training samples.

Verification error rate below 15% with hundreds of training Tweets.

Abstract

Establishing authorship of online texts is fundamental to combat cybercrimes. Unfortunately, text length is limited on some platforms, making the challenge harder. We aim at identifying the authorship of Twitter messages limited to 140 characters. We evaluate popular stylometric features, widely used in literary analysis, and specific Twitter features like URLs, hashtags, replies or quotes. We use two databases with 93 and 3957 authors, respectively. We test varying sized author sets and varying amounts of training/test texts per author. Performance is further improved by feature combination via automatic selection. With a large number of training Tweets (>500), a good accuracy (Rank-5>80%) is achievable with only a few dozens of test Tweets, even with several thousands of authors. With smaller sample sizes (10-20 training Tweets), the search space can be diminished by 9-15% while keeping a high chance that the correct author is retrieved among the candidates. In such cases, automatic attribution can provide significant time savings to experts in suspect search. For completeness, we report verification results. With few training/test Tweets, the EER is above 20-25%, which is reduced to < 15% if hundreds of training Tweets are available. We also quantify the computational complexity and time permanence of the employed features.