View Proposal


Proposer
Simona Frenda
Title
Detection of information disorder online
Goal
Create, fine-tune, or prompt models to detect misrepresentations of events and persons involved in facts described in newspapers online.
Description
Information Disorder is a conceptual framework that details the various components and factors of commonly called fake news [1]. In this project, we will explore a multilingual dataset of news [2] composed of news contents and textual and contextual factors that characterize misinformation. We can: develop systems that are able to identify spans of texts in news articles that are misinformative: these spans should contain misrepresentation of events or persons involved in the news. generate explanations about them, detailing the reason of their problematic nature. The dataset contains spans and their explanations created by human annotators coming from different countries. This information is relevant for the evaluation of the developed models.
Resources
[1] Wardle, C., & Derakhshan, H. (2017). Information disorder: Toward an interdisciplinary framework for research and policymaking (Vol. 27, pp. 1-107). Strasbourg: Council of Europe. [2] https://huggingface.co/datasets/aequa-tech/information-disorder-sample
Background
Url
Difficulty Level
Easy
Ethical Approval
None
Number Of Students
0
Supervisor
Simona Frenda
Keywords
bias detection, calibration of models, multiple annotated corpora
Degrees
Bachelor of Science in Computer Science
Master of Science in Artificial Intelligence
Master of Science in Artificial Intelligence with SMI
Master of Science in Data Science
Bachelor of Science in Computing Science
BSc Data Sciences