The future of AI-assisted individualized learning includes computer vision to inform intelligent tutors and teachers about student affect, motivation and performance. Facial expression recognition is essential in recognizing subtle differences when students ask for hints or fail to solve problems. Facial features and classification labels enable intelligent tutors to predict students’ performance and recommend activities. Videos can capture students’ faces and model their effort and progress; machine learning classifiers can support intelligent tutors to provide interventions. One goal of this research is to support deep dives by teachers to identify students’ individual needs through facial expression and to provide immediate feedback. Another goal is to develop data-directed education to gauge students’ pre-existing knowledge and analyze real-time data that will engage both teachers and students in more individualized and precision teaching and learning. This paper identifies three phases in the process of recognizing and predicting student progress based on analyzing facial features: Phase I: Collecting datasets and identifying salient labels for facial features and student attention/engagement; Phase II: Building and training deep learning models of facial features; and Phase III: Predicting student problem-solving outcome. © 2023 Copyright for this paper by its authors.
24th International Conference on Artificial Intelligence in Education Workshop
Woolf, Beverly; Betke, Margrit; Yu, Hao; Bargal, Sarah Adel; Arroyo, Ivan; Magee, John J. IV; Allessio, Danielle; and Rebelsky, William, "FACE READERS: The Frontier of Computer Vision and Math Learning" (2023). Computer Science. 6.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
© 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)