ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Ao, Wen, Yuxi, Zhang, Jiayi, Wen, Yunge, Zhao, Yibo, Prakash, Alok, Salazar-Gómez, Andrés F., Liang, Paul Pu, Zhao, Jinhua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915506799247360
author Qu, Ao
Wen, Yuxi
Zhang, Jiayi
Wen, Yunge
Zhao, Yibo
Prakash, Alok
Salazar-Gómez, Andrés F.
Liang, Paul Pu
Zhao, Jinhua
author_facet Qu, Ao
Wen, Yuxi
Zhang, Jiayi
Wen, Yunge
Zhao, Yibo
Prakash, Alok
Salazar-Gómez, Andrés F.
Liang, Paul Pu
Zhao, Jinhua
contents Classroom observation -- one of the most effective methods for teacher development -- remains limited due to high costs and a shortage of expert coaches. We present ClassMind, an AI-driven classroom observation system that integrates generative AI and multimodal learning to analyze classroom artifacts (e.g., class recordings) and deliver timely, personalized feedback aligned with pedagogical practices. At its core is AVA-Align, an agent framework that analyzes long classroom video recordings to generate temporally precise, best-practice-aligned feedback to support teacher reflection and improvement. Our three-phase study involved participatory co-design with educators, development of a full-stack system, and field testing with teachers at different stages of practice. Teachers highlighted the system's usefulness, ease of use, and novelty, while also raising concerns about privacy and the role of human judgment, motivating deeper exploration of future human--AI coaching partnerships. This work illustrates how multimodal AI can scale expert coaching and advance teacher development.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18020
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI
Qu, Ao
Wen, Yuxi
Zhang, Jiayi
Wen, Yunge
Zhao, Yibo
Prakash, Alok
Salazar-Gómez, Andrés F.
Liang, Paul Pu
Zhao, Jinhua
Human-Computer Interaction
Classroom observation -- one of the most effective methods for teacher development -- remains limited due to high costs and a shortage of expert coaches. We present ClassMind, an AI-driven classroom observation system that integrates generative AI and multimodal learning to analyze classroom artifacts (e.g., class recordings) and deliver timely, personalized feedback aligned with pedagogical practices. At its core is AVA-Align, an agent framework that analyzes long classroom video recordings to generate temporally precise, best-practice-aligned feedback to support teacher reflection and improvement. Our three-phase study involved participatory co-design with educators, development of a full-stack system, and field testing with teachers at different stages of practice. Teachers highlighted the system's usefulness, ease of use, and novelty, while also raising concerns about privacy and the role of human judgment, motivating deeper exploration of future human--AI coaching partnerships. This work illustrates how multimodal AI can scale expert coaching and advance teacher development.
title ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI
topic Human-Computer Interaction
url https://arxiv.org/abs/2509.18020