Scalable and reliable anomaly detection on Dynamic Graph based on link prediction to identify disinformation - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2022

Scalable and reliable anomaly detection on Dynamic Graph based on link prediction to identify disinformation

Abstract

As social networks take an ever-prominent role in information access, combating disinformation becomes increasingly important. Given current volumes of data, automated approaches for the detection of disinformation are the only ones able to offer an online solution. We formalize disinformation as an anomaly in the organic evolution of the network, in terms of users, content or coordination. To identify it, we propose a solution based on Temporal Graph Networks (TGN) adapted to the detection of anomalies and completed with a reliability module which permits users to trade precision for recall. Inheriting the performances of TGN, this solution is able to scale up, work on continuous time settings, and handle multimodality (text, image and video). Moreover, when compared to existing models, our approach outperforms state-of-the-art solutions for anomaly detection in dynamic graphs on several classical datasets. Lastly, it has been tested on a Twitter dataset of the French presidential election of 2022, providing useful insights on manipulation during the campaign.
Fichier principal
Vignette du fichier
LoG_Conference_2022_preprint.pdf (1.27 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03866467 , version 1 (22-11-2022)

Identifiers

  • HAL Id : hal-03866467 , version 1

Cite

Victor Chomel, Nathanaël Cuvelle-Magar, David Chavalarias. Scalable and reliable anomaly detection on Dynamic Graph based on link prediction to identify disinformation. 2022. ⟨hal-03866467⟩
262 View
239 Download

Share

Gmail Mastodon Facebook X LinkedIn More