EANN

TLDR

Fake news on social media increasingly exploits multimedia content, posing a major public concern, especially as new events emerge and existing methods struggle to generalize beyond event‑specific features. This study introduces the Event Adversarial Neural Network (EANN) to learn event‑invariant representations that improve fake news detection on newly arrived events. EANN comprises a multi‑modal feature extractor that captures textual and visual cues, a fake news detector that learns discriminative representations, and an event discriminator that removes event‑specific signals to retain shared features across events, evaluated on Weibo and Twitter multimedia datasets. Experimental results demonstrate that EANN surpasses state‑of‑the‑art baselines and successfully learns transferable feature representations for fake news detection.

Abstract

As news reading on social media becomes more and more popular, fake news becomes a major issue concerning the public and government. The fake news can take advantage of multimedia content to mislead readers and get dissemination, which can cause negative effects or even manipulate the public events. One of the unique challenges for fake news detection on social media is how to identify fake news on newly emerged events. Unfortunately, most of the existing approaches can hardly handle this challenge, since they tend to learn event-specific features that can not be transferred to unseen events. In order to address this issue, we propose an end-to-end framework named Event Adversarial Neural Network (EANN), which can derive event-invariant features and thus benefit the detection of fake news on newly arrived events. It consists of three main components: the multi-modal feature extractor, the fake news detector, and the event discriminator. The multi-modal feature extractor is responsible for extracting the textual and visual features from posts. It cooperates with the fake news detector to learn the discriminable representation for the detection of fake news. The role of event discriminator is to remove the event-specific features and keep shared features among events. Extensive experiments are conducted on multimedia datasets collected from Weibo and Twitter. The experimental results show our proposed EANN model can outperform the state-of-the-art methods, and learn transferable feature representations.