|
Fake News Detection and Content Categorization
Third-party funded project |
Project title |
Fake News Detection and Content Categorization |
Principal Investigator(s) |
Schuldt, Heiko
|
Organisation / Research unit |
Departement Mathematik und Informatik / Databases and Information Systems (Schuldt) |
Department |
Departement Mathematik und Informatik / Databases and Information Systems (Schuldt) |
Project start |
01.07.2020 |
Probable end |
31.03.2021 |
Status |
Completed |
Abstract |
The main innovative content of the planned work is the scalable classification and contextualization of news items, enriched with the detection and analysis of disinformation based on multi-modal cues (i.e., taking different types of media into account). Differentiating opinionated journalism from objective news reporting, real stories from rumors, and hoaxes from maliciously crafted disinformation has become a major challenge and has led to new terms like fake news, post-truth, alternative facts, and “truthiness”. Fact-checking platforms like FactCheck.org or PolitiFact.com employ journalists and volunteers to manually verify articles and speeches as they are being published. However, the task of manually verifying and labeling news articles is arduous, expensive, prone to error or personal bias, and does not scale. Out of the many projects that aim at automatically classifying and analyzing news items, none of them jointly considers text and embedded multimedia content. |
Keywords |
classification and contextualization of news items |
Financed by |
Innovation Promotion Agency CTI
|
|
|
|
MCSS v5.8 PRO. 0.429 sec, queries - 0.000 sec
©Universität Basel | Impressum
| |
25/04/2024
Research Database / FORSCHUNGSDATENBANK
|