LG4AV: Combining Language Models and Graph Neural Networks for Author Verification

TL;DR

LG4AV is a novel method that combines language models and graph neural networks to verify authorship using limited text data and relational information, especially suited for scholarly and social media contexts.

Contribution

The paper introduces LG4AV, a new approach that integrates language models with graph neural networks for authorship verification, addressing challenges with short, uniform texts.

Findings

Incorporating co-authorship relations improves verification accuracy.

The model performs well with limited text data like abstracts and titles.

Graph neural networks enhance authorship verification in bibliometric settings.

Abstract

The automatic verification of document authorships is important in various settings. Researchers are for example judged and compared by the amount and impact of their publications and public figures are confronted by their posts on social media platforms. Therefore, it is important that authorship information in frequently used web services and platforms is correct. The question whether a given document is written by a given author is commonly referred to as authorship verification (AV). While AV is a widely investigated problem in general, only few works consider settings where the documents are short and written in a rather uniform style. This makes most approaches unpractical for online databases and knowledge graphs in the scholarly domain. Here, authorships of scientific publications have to be verified, often with just abstracts and titles available. To this point, we present our novel approach LG4AV which combines language models and graph neural networks for authorship verification. By directly feeding the available texts in a pre-trained transformer architecture, our model does not need any hand-crafted stylometric features that are not meaningful in scenarios where the writing style is, at least to some extent, standardized. By the incorporation of a graph neural network structure, our model can benefit from relations between authors that are meaningful with respect to the verification process. For example, scientific authors are more likely to write about topics that are addressed by their co-authors and twitter users tend to post about the same subjects as people they follow. We experimentally evaluate our model and study to which extent the inclusion of co-authorships enhances verification decisions in bibliometric environments.