Responsible and Explainable Fact-Checking through Fine-Grained Factual Reasoning

The constant increase of misinformation around the world has become an urgent global problem. Nowadays, most existing automated fact-checking addresses article-level analysis of news. Nevertheless, news credibility and fact-checking systems at scale require accurate prediction, since each document comprises multiple sentences, which may contain factual information, bias, and misinformation. Furthermore, due to the high complexity of interpretability for automated machine learning models, there is a lack of transparency that poses unwanted risks for misinformation applications. In order to address the current limitations and provide advances towards effectively countering misinformation on the web and social media in Brazil, we already created accurate and expert annotation schemas and developed data resources (e.g. FactNews dataset and Central de Fatos repository) for sentence-level factuality prediction of news articles. As research to be developed in this project, we aim to investigate and propose responsible and explainable methods for fact-checking that use factual reasoning to provide explanations on the reliability and veracity of news articles at a fine-grained level. The proposed fact-checking will compute an overall trustworthiness the score of the entire document considering the sentence-level explications of factuality and veracity provided by the prediction of news articles’ factuality and media bias including propaganda, and the identification of veracity evidence from different repositories.

Leader
  • Francielle Vargas. Institute of Mathematics and Computer Sciences, University of São Paulo, Brazil
Team
  • Zohar Rabinovich. Viterbi School of Engineering, University of Southern California, United States
  • Kokil Jaidka. Centre for Trusted Internet and Community, National University of Singapore, Singapore
  • Jonas D'Alessandro. Department of Linguistics, Federal University of Minas Gerais, Brazil
  • Isadora Salles. Department of Computer Science, Federal University of Minas Gerais, Brazil
  • Fabrício Benevenuto. Department of Computer Science, Federal University of Minas Gerais, Brazil

Publications

    • Rhetorical Structure Approach for Online Deception Detection: A Survey
      Francielle Vargas, Jonas D'Alessandro, Zohar Rabinovich, Fabrício Benevenuto, Thiago A.S. Pardo
      13th Conference on Language Resources and Evaluation (LREC 2022). pp. 5906‑5915. Marseille, France. see

    • Toward Discourse-Aware Models for Multilingual Fake News Detection
      Francielle Vargas, Fabrício Benevenuto, Thiago A.S. Pardo
      Recent Advances in Natural Language Processing (RANLP 2021). pp. 210-218. Held Online. see
Resources
Method
Dataset
  • FactNews: Sentence-level annotated dataset to predict factually and media bias
System

Sponsorship