(TNS) – WORCESTER – A new government-funded research project at Worcester Polytechnic Institute aims to use artificial intelligence in hopes of revolutionizing the way teachers evaluate their own performance in the classroom.
Computer science professor Jacob Whitehill and his colleagues have received a $750,000, three-year grant from the National Science Foundation to develop the Automatic Classroom Observation Recognition Neural Network platform, or ACORN for short, which will combine machine learning, natural language processing, and elements of psychology and educational theory to deliver rapid feedback on teacher-student interactions.
"I've always loved teaching – I really enjoy the dynamics between myself and my students," Mr. Whitehill said, adding that he's been particularly fascinated with finding a way to identify the characteristics of a positive exchange between instructor and pupil.
Currently, teachers rely on one-on-one and group feedback, as well as some video-aided assessment, to evaluate those interactions. Mr. Whitehill believes ACORN could allow them to critique themselves not only much more frequently, but also without the pressure of a peer or supervisor being involved.
"This kind of technology allows them to get objective feedback on their own teaching every day if they wanted to," he said. "And they don't have to worry about it being seen by anyone else."
ACORN, which is based on automatic facial and emotion recognition technology, essentially involves showing a machine hundreds of videos of classroom interactions and teaching it to identify physiological and speech cues – tone of voice and eye contact, for example – that indicate an effective interaction with a student. Using a heat map, for instance, ACORN could pinpoint when a teacher is showing emotional support of a student, and then share that information with the Classroom Observation Interactive Learning System, or COILS – a complementary technology to ACORN that Mr. Whitehill and his team also plan to develop – to be synthesized into an interactive training exercise for that instructor.
Working with Mr. Whitehill on the project will be WPI professors Erin Ottmar and Lane Harrison, as well as Jennifer LoCasale-Crouch, a professor at the University of Virginia's Curry School of Education. Undergraduate and graduate students at WPI will assist.
In the Worcester schools, teachers occasionally use technology, including video, to brush up on their skills, according to Magdalena Ganias, director of curriculum and professional learning.
"Some teachers do ask someone to videotape them, so they can watch themselves" in action, she said, or watch videos of other teachers being critiqued.
But she and Sarah Kyriazis, the school district's manager of instructional technology and digital learning, said they wouldn't want to see technology completely replace human interaction in professional development.
"I think there's a lot of research showing that there's a huge jump in professional learning success when teachers have coaching and modeling in the classroom," Ms. Kyriazis said.
Neither administrator was ready last week to speculate about the potential of the AI- based approach being developed at WPI.
Mr. Whitehill said ACORN and COILS aren't intended to replace conventional interpersonal teacher training exercises.
"This is such a hard artificial intelligence task," he said. "We won't be able to analyze a real classroom environment like a human can."
But he hopes the technology could be a low-cost supplemental professional development tool, and one that is intuitive enough for teachers to do on their own. Mr. Whitehill intends to make it a free service to schools.
"This is a very exploratory, ambitious project," he said. He said it could be a decade before a finished product is finally available for schools to use.
In the meantime, Mr. Whitehill and his research team will work toward the goal of producing "high-quality research" to propel the project even after the government grant expires in three years.
©2018 Telegram & Gazette, Worcester, Mass. Distributed by Tribune Content Agency, LLC.