Chancellor and Terveen Partner with Cisco to Fight Online Conferencing Bias
Department of Computer Science & Engineering assistant professor Stevie Chancellor and professor Loren Terveen collaborated with Cisco Research to examine and mitigate the effects of bias during online meetings.
The team interviewed individuals familiar with video conferencing and noted inequity that might occur on the platform. Working with Ph.D. students Mo Houtti and Moyan Zhou, there were indications of bias based on the behavior of the host, whether cameras were on or off, or the popularity of the chat feature.
Chancellor and Terveen developed an artificial intelligence (AI) chatbot to mitigate partiality during video conferences. The AI is designed to notice patterns throughout the meeting and prompt the host to self-correct when potential bias is detected. The team will use that data to further explore trends and new ways to make video conferencing more equitable.
“Our Cisco collaborators have been supportive about what we’re doing while giving us the freedom to really investigate bias,” said Chancellor. “Through their work, they have given us insights into things they know from the industry perspective. Their ideas have helped us frame our overall contributions and shaped our ideas for the chatbot.”
Research will continue this spring with an evaluation of the chatbot’s ability to improve overall participation in video conferencing. They will then test the technology in a live workplace environment, continuing to collaborate with Cisco throughout the process.
Read the full story on the U of M Technology Commercialization website.