Article

Detecting disinformation with measures of discourse derailment using LLMs

2024-11-18

Abstract excerpt

<p>Social media presents both opportunities and risks to society. One risk includes the potential for the spread of disinformation, but methods for automatic detecting possible disinformation still mostly rely on low-level lexical cues. We present a new approach to the automatic detection of disinformation based on measuring discourse ‘derailment’ – messages that try to force the topic of discourse away from one t...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 059f23d5-bc8c-5c19-9aea-0e40ef2fdce8
DOI: 10.31234/osf.io/cspdw_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Detecting disinformation with measures of discourse derailment using LLMsDOI 10.31234/osf.io/cspdw_v1Read

Detecting disinformation with measures of discourse derailment using LLMsSemantic proximity Read

“Account suspension. Verify now”: using systemic-functional linguistics to improve phishing text advisories for vulnerable groupsSemantic proximity Read

DistilBERT: A Novel Approach to Detect Text Generated by Large Language Models (LLM)Semantic proximity Read

Unmasking AI-Generated Fake News Across Multiple DomainsSemantic proximity Read

Natural Language Processing (NLP) for Social Media Threat IntelligenceSemantic proximity Read

SafeSpeech: A Three-Module Pipeline for Hate Intensity Mitigation of Social Media Texts in Indic LanguagesSemantic proximity Read

On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled TrialSemantic proximity Read

Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and StereotypesSemantic proximity Read

Contrasting Linguistic Patterns in Human and LLM-Generated News TextSemantic proximity Read

Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behaviorSemantic proximity Read

<span class="word">The <span class="word"><span class="changedDisabled">Ten <span class="word"><span class="changedDisabled">Minutes <span class="word"><span class="changedDisabled">That <span class="word"><span class="changedDisabled">Shocked <span class="word">the <span class="word"><span class="changedDisabled">World. <span class="word">Teaching <span class="word">Generative <span class="word allCaps">AI <span class="word">to <span class="word"><span class="changedDisabled">Analyze <span cla…Semantic proximity Read

Cross-Dataset Generalization in Urdu Fake News Detection: An Empirical Study with XLM-RoBERTa and a Length Confound AnalysisSemantic proximity Read