Similarity Learning for Authorship Verification in Social Media

TL;DR

This paper introduces a novel neural network approach for authorship verification in social media, addressing challenges posed by short messages and diverse genres, and demonstrating significant performance improvements over traditional methods.

Contribution

A new neural network topology for similarity learning that enhances authorship verification accuracy on social media data with short and diverse texts.

Findings

Significant performance improvement over traditional n-gram based methods

Effective verification on short, diverse social media messages

Neural network topology adapts well to challenging datasets

Abstract

Authorship verification tries to answer the question if two documents with unknown authors were written by the same author or not. A range of successful technical approaches has been proposed for this task, many of which are based on traditional linguistic features such as n-grams. These algorithms achieve good results for certain types of written documents like books and novels. Forensic authorship verification for social media, however, is a much more challenging task since messages tend to be relatively short, with a large variety of different genres and topics. At this point, traditional methods based on features like n-grams have had limited success. In this work, we propose a new neural network topology for similarity learning that significantly improves the performance on the author verification task with such challenging data sets.