Detection of Human and Machine-Authored Fake News in Urdu

TL;DR

This paper introduces a new hierarchical detection method for identifying human and machine-generated fake news in Urdu, addressing challenges posed by advanced language models and low-resource language detection.

Contribution

It extends fake news detection to Urdu and incorporates machine-generated news detection with a hierarchical approach, improving accuracy and robustness.

Findings

Effective detection across four datasets

Improved accuracy with hierarchical strategy

Addresses low-resource language challenges

Abstract

The rise of social media has amplified the spread of fake news, now further complicated by large language models (LLMs) like ChatGPT, which ease the generation of highly convincing, error-free misinformation, making it increasingly challenging for the public to discern truth from falsehood. Traditional fake news detection methods relying on linguistic cues also becomes less effective. Moreover, current detectors primarily focus on binary classification and English texts, often overlooking the distinction between machine-generated true vs. fake news and the detection in low-resource languages. To this end, we updated detection schema to include machine-generated news with focus on the Urdu language. We further propose a hierarchical detection strategy to improve the accuracy and robustness. Experiments show its effectiveness across four datasets in various settings.