University of Oklahoma releases free tool for studying how AI chatbots affect human behavior
Researchers can now use ECHO, a free platform created at the University of Oklahoma, to run behavioral experiments involving conversational AI and human-AI interaction. The tool automates the technical setup required for studies examining how chatbots influence trust, learning, and decision-making.
ECHO-Evaluation of Chat, Human Behavior, and Outcomes-is an open source, low-code platform that lets researchers design experiments without extensive programming knowledge. Installation takes about 20 minutes, and the code is available on GitHub.
Jiqun Liu, an associate professor at the OU School of Library and Information Studies, created ECHO with graduate student Nischal Dinesh and Ran Yu, a senior researcher at GESIS-Leibniz Institute for the Social Sciences in Germany.
"When a researcher wants to build a study that integrates an AI chatbot, they can install our platform and easily add components," Liu said. "For most social science studies, ECHO will be easy to implement."
Why researchers need this tool now
The shift from keyword search engines to conversational AI systems is changing how people find and use information. Researchers are studying the effects of this change, but building experiments to measure human-AI interaction has required significant technical work.
ECHO removes that barrier. Researchers configure experimental workflows through an administrator dashboard while participants complete surveys and information-seeking tasks through a web interface. The platform automatically records behavior logs and responses as structured datasets ready for analysis.
Current research using the platform
Liu's lab is running several studies with ECHO. One examines how much information people retain when using an AI chatbot to research debated topics. Another, conducted with colleagues at OU Health Sciences, tests whether AI tools can improve access to information and advice about intimate partner violence.
Addressing human-AI friction
Liu said his goal in creating ECHO is to encourage what he calls "healthy friction" in AI system design. Research shows that because AI chatbots are often overly agreeable, people tend to trust inaccurate or biased information they receive.
"There are problems with human-AI interaction," Liu said. "As an information scientist, I can't solve all these problems. But what I can do is develop open-source systems, like ECHO, that others can use to boost their own study of these interactions."
Liu is encouraging researchers at other institutions to use ECHO and share feedback for improvements. The platform continues to be updated based on user experience.
Learn more: Read the research paper on arXiv. Access the code on GitHub.
Your membership also unlocks:
