In a digital landscape where misinformation spreads rapidly, a team from Arizona State University (ASU) has developed Skeptik, a browser-based tool designed to help readers identify logical fallacies in online news articles. The project brings together researchers from the School of Computing and Augmented Intelligence within the Ira A. Fulton Schools of Engineering and ASU’s Center for Strategic Communication.
Skeptik uses large language models similar to those found in modern artificial intelligence chatbots. These models are combined with human communication theory to detect and explain subtle flaws in arguments presented in news stories.
“Our goal isn’t to tell people what to think,” said Fan Lei, who led the project until earning his computer science doctoral degree from the Fulton Schools in 2025. “It’s to help them see how an argument is built, where it’s solid and where it might be taking shortcuts. We want to empower readers to think critically, not passively consume information.”
The tool marks sentences containing potential logical inconsistencies directly within articles. Readers can interact with these highlights for brief explanations, external evidence, or initiate a live chat with an AI model for further clarification. Each type of fallacy is color-coded and linked to an interactive sidebar that provides increasingly detailed explanations as users engage.
“People don’t always fall for misinformation because they’re careless,” Lei said. “They fall for it because persuasive writing often feels logical. We wanted to give readers a way to pause and ask, ‘Does this conclusion really follow from the evidence?’”
Ross Maciejewski, director of the School of Computing and Augmented Intelligence at ASU, received recognition at the VIS 2025 Conference in Vienna for his leadership in data visualization—a field closely related to projects like Skeptik.
The conceptual foundation for Skeptik comes from inoculation theory, which suggests that exposing individuals to small doses of misinformation along with explanations helps build resistance against future falsehoods. Steve Corman, professor emeritus at ASU’s Hugh Downs School of Human Communication and expert in strategic communication, contributed this perspective.
When Skeptik flags a potential fallacy, it presents its findings cautiously—using phrases such as “This may be an example of X”—and leaves final judgment up to readers.
“Good visualization and AI tools should help people think more clearly, not take the thinking away,” Maciejewski said. “Skeptik embodies that philosophy. It’s a system built to foster critical awareness.”
The interdisciplinary approach involved both technical development by engineers and guidance from communication scholars like Corman on making explanations accessible.
“Working with Professor Corman was eye-opening,” Lei said. “He helped us translate technical detection results into meaningful guidance that resonates with how people read, argue and form opinions. It’s a true human-AI collaboration.”
Currently able to detect nine common types of logical fallacies—including cherry-picking and red herring—the system links each instance visually within texts analyzed during case studies on topics such as climate change and public health.
Testing against the Ad Fontes Media dataset showed that sources rated as more biased tended also to contain more logical fallacies according to Skeptik’s analysis—a result suggesting that automated detection could complement traditional fact-checking methods when evaluating news credibility.
“There’s a real need for tools like Skeptik, ones that don’t tell people what to think but how to think about media content more critically,” Corman said. “We intentionally designed it not to say, ‘This statement is wrong,’ but rather, ‘Here’s why you should think about this statement more carefully.’”
Lei noted: “In an age of information overload, it’s easy to get cynical… But if we can build tools that make critical reading more interactive… we can restore some of that trust between journalists and audiences.”
Looking ahead, the team plans further enhancements including visualizations showing article logic flow or features allowing collaborative annotation by readers; they also hope educators will use Skeptik as part of classroom instruction on bias analysis.
“This kind of research captures the best of what the Fulton Schools stands for,” Maciejewski said. “It’s technically sophisticated but also deeply human. We’re building technology that doesn’t just process information. It helps people make sense of it.”
Arizona State University has been recognized nationally for its innovation efforts; U.S News & World Report named ASU number one in innovation for eight consecutive years based on nominations by university leaders across the country (https://news.asu.edu/20220911-university-news-asu-no-1-innovation-us-news-world-report-eighth-year?utm_source=twitter&utm_medium=asu&utm_campaign=ASURankings&utm_term=USNWR).
Additionally, ASU collaborates on other technology initiatives such as partnering with Argos Vision—a tech startup developing smart traffic cameras—to improve safety through data analysis in Phoenix (https://www.phoenix.gov/newsroom/street-transportation/2420).
