OU Data Scientist Unveils Free Software for Researching Human-AI Interactions

Source Domain: ou.edu

A University of Oklahoma data scientist, Jiqun Liu, has developed a free research tool called ECHO to help design AI systems that are equitable, efficient, and inclusive.
ECHO (Evaluation of Chat, Human Behavior, and Outcomes) is an open-source, low-code platform designed to facilitate behavioral experiments involving conversational AI, web search, and human-AI interaction.
Liu’s platform is aimed at reducing the front-end programming workload for researchers, allowing them to easily integrate AI chatbot and other components into their studies.
The ECHO platform is available for free on GitHub and includes a step-by-step video tutorial, with installation taking about 20 minutes.
Researchers using ECHO can configure experimental workflows with the help of an administrator dashboard, and participants can interact through a web-based interface.
ECHO aims to promote studies that analyze human-AI interactions to better understand how they influence learning, trust, and decision-making.
Liu’s research extends to various projects, including investigations on information retention during AI chatbot interactions and tests on AI tools improving information access related to intimate partner violence.
Liu hopes that the free availability of ECHO will encourage more researchers to include AI-human interaction designs in their work, fostering “healthy friction” in AI system design and evaluation.

You may have missed