HyperGraphDis: Leveraging Hypergraphs for Contextual and Social-Based Disinformation Detection

TL;DR

HyperGraphDis introduces a hypergraph-based model for detecting disinformation on Twitter, capturing social, relational, semantic, and topical features, and demonstrates superior accuracy and efficiency on multiple datasets.

Contribution

The paper presents HyperGraphDis, a novel hypergraph approach that effectively models complex social and semantic structures for disinformation detection, outperforming existing methods.

Findings

Achieves approximately 89.5% F1 score on COVID-19 dataset.

Reduces training time by 2.3 to 7.6 times compared to previous methods.

Speeds up inference by 1.3 to 6.8 times.

Abstract

In light of the growing impact of disinformation on social, economic, and political landscapes, accurate and efficient identification methods are increasingly critical. This paper introduces HyperGraphDis, a novel approach for detecting disinformation on Twitter that employs a hypergraph-based representation to capture (i) the intricate social structures arising from retweet cascades, (ii) relational features among users, and (iii) semantic and topical nuances. Evaluated on four Twitter datasets -- focusing on the 2016 U.S. Presidential election and the COVID-19 pandemic -- HyperGraphDis outperforms existing methods in both accuracy and computational efficiency, underscoring its effectiveness and scalability for tackling the challenges posed by disinformation dissemination. HyperGraphDis displays exceptional performance on a COVID-19-related dataset, achieving an impressive F1 score (weighted) of approximately 89.5%. This result represents a notable improvement of around 4% compared to the other state-of-the-art methods. Additionally, significant enhancements in computation time are observed for both model training and inference. In terms of model training, completion times are accelerated by a factor ranging from 2.3 to 7.6 compared to the second-best method across the four datasets. Similarly, during inference, computation times are 1.3 to 6.8 times faster than the state-of-the-art.