A Declarative Approach To Data Driven Fact Checking

Bonisiwe Shabane

-Dec 9, 2025, 11:29 PM

a declarative approach to data driven fact checking

Fact checking is an essential part of any investigative work. For linguistic, psychological and social reasons, it is an inherently human task. Yet, modern media make it increasingly difficult for experts to keep up with the pace at which information is produced. Hence, we believe there is value in tools to assist them in this process. Much of the effort on Web data research has been focused on coping with incompleteness and uncertainty. Comparatively, dealing with context has received less attention, although it is crucial in judging the validity of a claim.

For instance, what holds true in a US state, might not in its neighbors, e.g., due to obsolete or superseded laws. In this work, we address the problem of checking the validity of claims in multiple contexts. We define a language to represent and query facts across different dimensions. The approach is non-intrusive and allows relatively easy modeling, while capturing incompleteness and uncertainty. We describe the syntax and semantics of the language. We present algorithms to demonstrate its feasibility, and we illustrate its usefulness through examples.

#1 A Declarative Approach to Data-Driven Fact Checking Github: https://github.com/bojone/papers.cool Please read our Disclaimer before proceeding. For more interesting features, please visit kexue.fm and kimi.ai. Research output: Contribution to journal › Article › peer-review This study examined four fact checkers (Snopes, PolitiFact, Logically, and the Australian Associated Press FactCheck) using a data-driven approach.

First, we scraped 22,349 fact-checking articles from Snopes and PolitiFact and compared their results and agreement on verdicts. Generally, the two fact checkers agreed with each other, with only one conflicting verdict among 749 matching claims after adjusting minor rating differences. Next, we assessed 1,820 fact-checking articles from Logically and the Australian Associated Press FactCheck and highlighted the differences in their fact-checking behaviors. Major events like the COVID-19 pandemic and the presidential election drove increased the frequency of fact-checking, with notable variations in ratings and authors across fact checkers. Research output: Contribution to journal › Article › peer-review N1 - Publisher Copyright: © 2023, Harvard Kennedy School.

All rights reserved. N2 - This study examined four fact checkers (Snopes, PolitiFact, Logically, and the Australian Associated Press FactCheck) using a data-driven approach. First, we scraped 22,349 fact-checking articles from Snopes and PolitiFact and compared their results and agreement on verdicts. Generally, the two fact checkers agreed with each other, with only one conflicting verdict among 749 matching claims after adjusting minor rating differences. Next, we assessed 1,820 fact-checking articles from Logically and the Australian Associated Press FactCheck and highlighted the differences in their fact-checking behaviors. Major events like the COVID-19 pandemic and the presidential election drove increased the frequency of fact-checking, with notable variations in ratings and authors across fact checkers.

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Please note: Providing information about references and citations is only possible thanks to to the open metadata APIs provided by crossref.org and opencitations.net.

If citation data of your publications is not openly available yet, then please consider asking your publisher to release your citation data to the public. For more information please see the Initiative for Open Citations (I4OC). Please also note that there is no way of submitting missing references or citation data directly to dblp. Please also note that this feature is work in progress and that it is still far from being perfect. That is, in particular, JavaScript is requires in order to retrieve and display any references and citations for this record.

references and citations temporaily disabled To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q. With so much information at our fingertips, the need for accurate and reliable data has never been greater.

Relying on data-driven fact-checking can help us better understand what’s real and reputable over what’s false and misleading, but in addition to a technology-based approach, we also need to develop our own critical thinking... But as the case with any kind of skill development, where do you even begin? In this article, we’ll take a closer look at what data-driven fact-checking actually means, how it’s implemented and how you can develop your own critical thinking skills alongside the developments in technology to accurately... With the rise of fake news, misinformation and information overload, it’s easy to turn passive and just accept whatever comes your way as fact. It’s also a very risky strategy that if left unchecked, can have real-world consequences. By developing data-driven fact-checking skills, you empower yourself to understand truth from fiction and make more informed decisions by pulling from the most accurate information around you.

Developing your data-driven fact-checking skills isn’t something that can happen overnight, but the more you familiarize yourself with the process and use it when evaluating the credibility of an article, a picture or a... That means: Not all sources are created equal. You often can’t tell how credible a specific source is just by looking at the title or the author. Take a deeper look at the author’s credentials and any affiliations that they’re part of which might reveal human biases within the article. Misinformation and disinformation spread rapidly on social media, threatening public discourse, democratic processes, and social cohesion.

One promising strategy to address these challenges is to evaluate the trustworthiness of entire domains (source websites) as a proxy for content credibility. This approach demands methods that are both scalable and data-driven. However, current solutions like NewsGuard and MBFC rely on expert assessments, cover only a limited number of domains, and often require paid subscriptions. These constraints limit their usefulness for large-scale research.This study introduces a machine-learning-based system designed to assess the quality and trustworthiness of websites. We propose a data-driven approach that leverages a large dataset of expert-rated domains to predict credibility scores for previously unseen domains using domain-level features. Our supervised regression model achieves moderate performance, with a mean absolute error of 0.12.

Using feature importance analysis, we found that PageRank-based features provided the greatest reduction in prediction error, confirming that link-based indicators play a central role in domain trustworthiness. This highlights the importance of highly referenced domains in reliable news dissemination. This approach can also help fact-checkers and social media platforms refine their credibility assessment strategies.The solution’s scalable design accommodates the continuously evolving nature of online content, ensuring that evaluations remain timely and relevant. The framework enables continuous assessment of thousands of domains with minimal manual effort. This capability allows stakeholders (social media platforms, media monitoring organizations, content moderators, and researchers) to allocate resources more efficiently, prioritize verification efforts, and reduce exposure to questionable sources. Ultimately, this facilitates a more proactive and effective response to misinformation while also supporting robust public discourse and informed decision-making.

A Declarative Approach To Data Driven Fact Checking

People Also Search

Fact Checking Is An Essential Part Of Any Investigative Work.

For Instance, What Holds True In A US State, Might

#1 A Declarative Approach To Data-Driven Fact Checking Github: Https://github.com/bojone/papers.cool

First, We Scraped 22,349 Fact-checking Articles From Snopes And PolitiFact

All Rights Reserved. N2 - This Study Examined Four Fact