Jill Watson Now Fielding Questions on New AI-enabled Research Tool

A new artificially intelligent (AI) research tool that harnesses the power of the Smithsonian Institution’s massive Encyclopedia of Life (EOL) ecological database debuted this semester at Georgia Tech. 

The virtual ecological research assistant, known as VERA, was developed at Georgia Tech and enables students to perform virtual experiments to explain existing ecological systems or to predict possible outcomes based on variables they input into the tool.

Getting to Know VERA

“People using VERA have access to the EOL and can test a hypothesis using countless organisms, make as many changes to variables as they want, and study the effects on any ecosystem through real-time modeling,” said Sungeun An, human-centered computing Ph.D. student and lead developer of the AI system.

“This is a unique opportunity that doesn’t exist anywhere else.”

Although the EOL has extensive data entries for more than two million species, An says that VERA has an intuitive user interface and design that is relatively easy to use.

“Students don’t need extensive scientific knowledge or programming and math skills to use VERA. They can build a conceptual model with simple visual cues on the computer screen, such as dragging elements or selecting input options,” said An.

Combining the Strength of Two AIs

However, to get the most out of VERA, An says there can be a learning curve.

To flatten the curve and help students optimize their experience with VERA, An and her fellow researchers turned to Jill Watson, the famed AI-enabled virtual teaching assistant (TA) that premiered in 2016 supporting Georgia Tech’s online Master of Science in Computer Science (OMSCS) program.

Jill Watson answers student questions about VERA via the collaborative messaging app, Slack. These range from technical questions about the tool – “How do I add a new project” – to subject matter questions – “What is consumption rate?”

“Leveraging the Jill Watson virtual TA and VERA together is a powerful demonstration of how to scale technology to serve more populations and provide access to the world’s scientific knowledge,” said Ashok Goel, professor of Interactive Computing and director of the Design & Intelligence Lab, which created both AI agents.

Combining the strength of the two AI agents, said Goel, is part of an intentional approach to rethinking instructional design for online learning.

“VERA is a significant advancement for artificial intelligence in science education and meant to be used anywhere by anyone interested in science exploration, so making it as accessible as possible is key to the system’s adoption,” Goel said.

Students and others using VERA – it’s also publicly available and linked on the Smithsonian’s EOL homepage ­– can learn more through a video series produced by Georgia Tech.

The videos demonstrate VERA’s capabilities using kudzu growth in the southeastern United States as an example. The videos are co-hosted by Emily Weigel, School of Biological Sciences instructor for the biology course using VERA, and College of Computing faculty member Spencer Rugaber.

VERA research is funded by a grant from the National Science Foundation, #NSF-1636848.

For more information about Georgia Tech's emPRIZE, contact Joshua Preston, research communications manager.