Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: da Silva, Bruno Croso Cunha, Ferraz, Thomas Palmeira, Lopes, Roseli De Deus
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910709827239936
author da Silva, Bruno Croso Cunha
Ferraz, Thomas Palmeira
Lopes, Roseli De Deus
author_facet da Silva, Bruno Croso Cunha
Ferraz, Thomas Palmeira
Lopes, Roseli De Deus
contents Disinformation on social media poses both societal and technical challenges, requiring robust detection systems. While previous studies have integrated textual information into propagation networks, they have yet to fully leverage the advancements in Transformer-based language models for high-quality contextual text representations. This work addresses this gap by incorporating Transformer-based textual features into Graph Neural Networks (GNNs) for fake news detection. We demonstrate that contextual text representations enhance GNN performance, achieving 33.8% relative improvement in Macro F1 over models without textual features and 9.3% over static text representations. We further investigate the impact of different feature sources and the effects of noisy data augmentation. We expect our methodology to open avenues for further research, and we made code publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19193
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media
da Silva, Bruno Croso Cunha
Ferraz, Thomas Palmeira
Lopes, Roseli De Deus
Computation and Language
Artificial Intelligence
Machine Learning
Social and Information Networks
Disinformation on social media poses both societal and technical challenges, requiring robust detection systems. While previous studies have integrated textual information into propagation networks, they have yet to fully leverage the advancements in Transformer-based language models for high-quality contextual text representations. This work addresses this gap by incorporating Transformer-based textual features into Graph Neural Networks (GNNs) for fake news detection. We demonstrate that contextual text representations enhance GNN performance, achieving 33.8% relative improvement in Macro F1 over models without textual features and 9.3% over static text representations. We further investigate the impact of different feature sources and the effects of noisy data augmentation. We expect our methodology to open avenues for further research, and we made code publicly available.
title Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media
topic Computation and Language
Artificial Intelligence
Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2410.19193