Background
The rapid dissemination of news is an important factor for the global population to stay up to date with current events, or to make well-informed decisions in dynamic sectors like the stock market. Journalists typically include large amounts of quantitative information using data visualization to help enhance accessibility and comprehension of complex datasets. However, the propagation of misinformation and false news has also grown in recent years, leading to the undermining of public trust in news reporting. Current fact-checking efforts primarily focus on the factual integrity of the text in journal articles, which tends to neglect the impact of argumentation practices and the accuracy of data visualizations.
Invention Description
Researchers at Arizona State University have developed a new approach for combating potential misinformation in journalism using a hybrid framework that combines the analytical strengths of large language models (LLMs) and heuristic approaches. This framework includes the development of a web browser extension designed to annotate online news articles, highlighting potentially deceptive elements by analyzing fallacies and ensuring consistency between the article text and visual data. This dual analysis capability provides the public with a complete understanding of the data narrative, which helps protect them from consuming false news sources.
Potential Applications:
- Identification of misinformation or false narratives in news articles
- Protecting the public against misinformation in news articles
- Improving information verification
Benefits and Advantages:
- Effective – detects subtle fallacies that may be missed by other systems
- Specific – highlights the problem in reasoning with the logical fallacies
- Thorough – includes outbound links to additional information to help prove logical fallacies & enhance critical consumption of information
- Versatile – able to set different parameters and temperatures depending on the job