Variety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations

TL;DR

This paper introduces MISDER, a dynamic framework for misinformation detection that models the evolving social environment over time, outperforming static methods by capturing temporal changes in news veracity.

Contribution

The paper proposes a novel dynamic environmental representation framework for misinformation detection, incorporating temporal models like LSTM, ODE, and pre-trained systems to better reflect real-world news evolution.

Findings

MISDER outperforms static baselines on two datasets.

Dynamic modeling improves misinformation detection accuracy.

Temporal models effectively capture news veracity changes over time.

Abstract

The proliferation of misinformation across diverse social media platforms has drawn significant attention from both academic and industrial communities due to its detrimental effects. Accordingly, automatically distinguishing misinformation, dubbed as Misinformation Detection (MD), has become an increasingly active research topic. The mainstream methods formulate MD as a static learning paradigm, which learns the mapping between the content, links, and propagation of news articles and the corresponding manual veracity labels. However, the static assumption is often violated, since in real-world scenarios, the veracity of news articles may vacillate within the dynamically evolving social environment. To tackle this problem, we propose a novel framework, namely Misinformation detection with Dynamic Environmental Representations (MISDER). The basic idea of MISDER lies in learning a social environmental representation for each period and employing a temporal model to predict the representation for future periods. In this work, we specify the temporal model as the LSTM model, continuous dynamics equation, and pre-trained dynamics system, suggesting three variants of MISDER, namely MISDER-LSTM, MISDER-ODE, and MISDER-PT, respectively. To evaluate the performance of MISDER, we compare it to various MD baselines across 2 prevalent datasets, and the experimental results can indicate the effectiveness of our proposed model.