Making the Unseen Seen with an AI-assisted Propaganda Detection and Fact-Checking
Apollolytics employs Large Language Models aims at fighting propaganda and disinformation in digital news. It identifies propaganda techniques, fact-checks content, and provides explanations. This empowers users to think critically and discern media biases, enhancing democratic integrity.
Team
- Prof. Dr. Liudmila Zavolokina, UNIL Digital Innovation Lab
- Prof. Dr. Alexandre Bovet, UZH Institute of Mathematics
- Kilian Sprenkamp, UZH Digital Society Initiative
- Zoya Katashinskaya, UZH Digital Society Initiative
- Daniel Gordon Jones, UZH
- Dorian Quelle, UZH Institute of Mathematics
Publications
- Sprenkamp, Kilian, Daniel Gordon Jones, and Liudmila Zavolokina. “Large language models for propaganda detection.” arXiv preprint arXiv:2310.06422 (2023).
- Zavolokina, L., Sprenkamp, K., Katashinskaya, Z., Jones, D. G., & Schwabe, G. (2024, May). Think fast, think slow, think critical: designing an automated propaganda detection tool. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (pp. 1-24).
- Hoferer, N., Sprenkamp, K., Quelle, D. C., Jones, D. G., Katashinskaya, Z., Bovet, A., & Zavolokina, L. (2025, April). Effective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinking. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (pp. 1-13).
- Zavolokina, L., Sprenkamp, K., Katashinskaya, Z., & Jones, D. G. (2025). Biased by design: Leveraging Inherent AI Biases to Enhance Critical Thinking of News Readers. ECIS 2025 Proceedings. 8. https://aisel.aisnet.org/ecis2025/hci/hci/8