Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning

TL;DR

This paper proposes Pref-FEND, a framework that integrates pattern- and fact-based fake news detection models by learning their preferences, resulting in improved detection accuracy on real-world datasets.

Contribution

It introduces a novel preference-aware framework that models and leverages the complementary preferences of pattern- and fact-based fake news detection methods.

Findings

Pref-FEND improves detection accuracy over individual models.

The framework effectively captures and utilizes model preferences.

Experiments demonstrate enhanced performance on real-world datasets.

Abstract

To defend against fake news, researchers have developed various methods based on texts. These methods can be grouped as 1) pattern-based methods, which focus on shared patterns among fake news posts rather than the claim itself; and 2) fact-based methods, which retrieve from external sources to verify the claim's veracity without considering patterns. The two groups of methods, which have different preferences of textual clues, actually play complementary roles in detecting fake news. However, few works consider their integration. In this paper, we study the problem of integrating pattern- and fact-based models into one framework via modeling their preference differences, i.e., making the pattern- and fact-based models focus on respective preferred parts in a post and mitigate interference from non-preferred parts as possible. To this end, we build a Preference-aware Fake News Detection Framework (Pref-FEND), which learns the respective preferences of pattern- and fact-based models for joint detection. We first design a heterogeneous dynamic graph convolutional network to generate the respective preference maps, and then use these maps to guide the joint learning of pattern- and fact-based models for final prediction. Experiments on two real-world datasets show that Pref-FEND effectively captures model preferences and improves the performance of models based on patterns, facts, or both.