Think Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Tool
Liudmila Zavolokina, Kilian Sprenkamp, Zoya Katashinskaya, Daniel Gordon Jones, Gerhard Schwabe
摘要
In today's digital age, characterized by rapid news consumption and increasing vulnerability to propaganda, fostering citizens' critical thinking is crucial for stable democracies. This paper introduces the design of ClarifAI, a novel automated propaganda detection tool designed to nudge readers towards more critical news consumption by activating the analytical mode of thinking, following Kahneman's dual-system theory of cognition. Using Large Language Models, ClarifAI detects propaganda in news articles and provides context-rich explanations, enhancing users' understanding and critical thinking. Our contribution is threefold: first, we propose the design of ClarifAI; second, in an online experiment, we demonstrate that this design effectively encourages news readers to engage in more critical reading; and third, we emphasize the value of explanations for fostering critical thinking. The study thus offers both a practical tool and useful design knowledge for mitigating propaganda in digital news.
• Human-centered computing ! Human computer interaction (HCI); Empirical studies in HCI.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper7
- The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge WorkersHao-Ping (Hank) Lee, Advait Sarkar, Lev Tankelevitch, Ian Drosos 等CHI 2025 · 被引用 690 次
- How CO2STLY Is CHI? The Carbon Footprint of Generative AI in HCI Research and What We Should Do About ItNanna Inie, Jeanette Falk, Raghavendra SelvanCHI 2025 · 被引用 33 次
- How Do HCI Researchers Study Cognitive Biases? A Scoping ReviewNattapat Boonprakong, Benjamin Tag, Jorge Gonçalves, Tilman DinglerCHI 2025 · 被引用 19 次
- Media Bias Detector: Designing and Implementing a Tool for Real-Time Selection and Framing Bias Analysis in News CoverageJenny S. Wang, Samar Haider, Amir Tohidi, Anushkaa Gupta 等CHI 2025 · 被引用 11 次
- Behavior Change Interventions Combating Online Misinformation: A Scoping ReviewLoukas Konstantinou, Evangelos KarapanosCHI 2025 · 被引用 11 次
它引用的顶会 Paper9
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Explanations Can Reduce Overreliance on AI Systems During Decision-MakingHelena Vasconcelos, Matthew Jörke, Madeleine Grunde-McLaughlin, Tobias Gerstenberg 等CSCW 2023 · 被引用 362 次
- From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP ModelsShangbin Feng, Chan Young Park, Yuhan Liu, Yulia TsvetkovACL 2023 · 被引用 117 次
- Exploring Lightweight Interventions at Posting Time to Reduce the Sharing of Misinformation on Social MediaFarnaz Jahanbakhsh, Amy X. Zhang, Adam J. Berinsky, Gordon Pennycook 等CSCW 2021 · 被引用 116 次
- Exploring the Use of Personalized AI for Identifying Misinformation on Social MediaFarnaz Jahanbakhsh, Yannis Katsis, Dakuo Wang, Lucian Popa 等CHI 2023 · 被引用 42 次
相关 Paper
- Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical ReasoningZhaodan Zhang, Jin Zhang, Jiafeng Guo, Xueqi ChengACL 2026
- Discourse Structures Guided Fine-grained Propaganda IdentificationYuanyuan Lei, Ruihong HuangEMNLP 2023
- CoNewsReader: Supporting Comprehensive Understanding and Raising Critical Thoughts on Social Media News Through CommentsKangyu Yuan, Guanzheng Chen, Sizhe Liang, Hehai Lin 等CSCW 2026
- Deceptive Explanations by Large Language Models Lead People to Change their Beliefs About Misinformation More Often than Honest ExplanationsValdemar Danry, Pat Pataranutaporn, Matthew Groh, Ziv EpsteinCHI 2025 · 被引用 32 次
- Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda DetectionRuize Wang, Duyu Tang, Nan Duan, Wanjun Zhong 等EMNLP 2020 · 被引用 3 次
