Semantic similarity models for automated fact-checking: ClaimCheck as a claim matching tool

Larraz, Irene; Míguez, Rubén; Sallicati, Francesca

doi:10.3145/epi.2023.may.21

EPI

2023

DOI: 10.3145/epi.2023.may.21

|View full text |Cite

Semantic similarity models for automated fact-checking: ClaimCheck as a claim matching tool

Irene Larraz,

Rubén Míguez,

Francesca Sallicati

Abstract: This article presents the experimental design of ClaimCheck, an artificial intelligence tool for detecting repeated falsehoods in political discourse using a semantic similarity model developed by the fact-checking organization Newtral in collaboration with ABC Australia. The study reviews the state of the art in algorithmic fact-checking and proposes a definition of claim matching. Additionally, it outlines the scheme for annotating similar sentences and presents the results of experiments conducted with the … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article5

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 6 publications

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

DisTrack: A New Tool For Semi-automatic Misinformation Tracking in Online Social Networks

Villar-Rodríguez,

Huertas-García,

Martín

et al. 2024

Cogn Comput

View full text Add to dashboard Cite

DisTrack: A New Tool For Semi-automatic Misinformation Tracking in Online Social Networks

Villar-Rodríguez,

Huertas-García,

Martín

et al. 2024

Cogn Comput

View full text Add to dashboard Cite

Generative Artificial Intelligence for Journalistic Content in Ibero-America : Perceptions, Challenges and Regional Projections

Apablaza-Campos,

Wilches Tinjacá,

Salaverría

2024

BiD: Textos Universitaris De Biblioteconomia I Documentació

View full text Add to dashboard Cite

Introduction: The increasing availability of artificial intelligence (AI) tools has brought with it various, increasingly advanced, uses for content production. Digital media editors have not been immune to the phenomenon, which is why there is growing interest, both professional and academic, regarding its possible uses. Objectives: In this paper we seek to detect the experiences, challenges and projections regarding the use of artificial intelligence in the generation of news content. In turn, the specific objectives aim both to offer a general overview of journalistic experiences with AI and to study the results of a survey regarding the use of this technology in the production of content in Ibero-America. Methodology: A survey was conducted among 154 participants through a cycle of webinars held at four universities in Ibero-America during the second semester of 2023, corresponding to 14 countries in the region, including academics, researchers and students of Journalism (and related degrees in Social Communication), along with managers and journalists from prominent media outlets. Results: although journalistic experiences with AI are still incipient in the region, the responses obtained show that most participants use generative AI tools every week, there is greater knowledge (and preference) for ChatGPT, and there is a consensus regarding how artificial intelligence can bring great benefits if it has the proper regulations.

show abstract

Combating Repeated Lies: The Impact of Fact-Checking on Persistent Falsehoods by Politicians

Larraz,

Salaverría,

Serrano-Puche

2024

MaC

View full text Add to dashboard Cite

The rise of repeated false claims within political discourse is undermining fact-checking efforts. By reiterating similar statements that perpetuate previous falsehoods, political actors shift from misinformation to deliberate disinformation and even propagandistic tactics. Through an analysis of 1,204 political fact-checks conducted by the Spanish fact-checking organization Newtral, this study quantifies and characterizes the prevalence of repeated false claims in political discourse, revealing that a substantial 24.8% of false statements are repeated, with each being repeated an average of four times. By delving into the nature and types of claims most susceptible to recurrence, the study identifies five primary patterns employed by political actors: nuanced variations, data manipulation, multilateral attacks, discourse qualification, and cumulative repetition. These tactics blur the lines between deception and self-correction. The annotated database of these repeated false statements can serve as a valuable resource for exploratory qualitative analysis as well as claim-matching research in automated fact-checking.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Semantic similarity models for automated fact-checking: ClaimCheck as a claim matching tool

Cited by 6 publications

References 22 publications

DisTrack: A New Tool For Semi-automatic Misinformation Tracking in Online Social Networks

DisTrack: A New Tool For Semi-automatic Misinformation Tracking in Online Social Networks

Generative Artificial Intelligence for Journalistic Content in Ibero-America : Perceptions, Challenges and Regional Projections

Combating Repeated Lies: The Impact of Fact-Checking on Persistent Falsehoods by Politicians

Contact Info

Product

Resources

About