Dude, where's my utterance? Evaluating the effects of automatic segmentation and transcription on CPS detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Venkatesha, Videep, Bradford, Mariah, Blanchard, Nathaniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909677662502912
author Venkatesha, Videep
Bradford, Mariah
Blanchard, Nathaniel
author_facet Venkatesha, Videep
Bradford, Mariah
Blanchard, Nathaniel
contents Collaborative Problem-Solving (CPS) markers capture key aspects of effective teamwork, such as staying on task, avoiding interruptions, and generating constructive ideas. An AI system that reliably detects these markers could help teachers identify when a group is struggling or demonstrating productive collaboration. Such a system requires an automated pipeline composed of multiple components. In this work, we evaluate how CPS detection is impacted by automating two critical components: transcription and speech segmentation. On the public Weights Task Dataset (WTD), we find CPS detection performance with automated transcription and segmentation methods is comparable to human-segmented and manually transcribed data; however, we find the automated segmentation methods reduces the number of utterances by 26.5%, impacting the the granularity of the data. We discuss the implications for developing AI-driven tools that support collaborative learning in classrooms.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dude, where's my utterance? Evaluating the effects of automatic segmentation and transcription on CPS detection
Venkatesha, Videep
Bradford, Mariah
Blanchard, Nathaniel
Human-Computer Interaction
Computation and Language
Computers and Society
Audio and Speech Processing
Collaborative Problem-Solving (CPS) markers capture key aspects of effective teamwork, such as staying on task, avoiding interruptions, and generating constructive ideas. An AI system that reliably detects these markers could help teachers identify when a group is struggling or demonstrating productive collaboration. Such a system requires an automated pipeline composed of multiple components. In this work, we evaluate how CPS detection is impacted by automating two critical components: transcription and speech segmentation. On the public Weights Task Dataset (WTD), we find CPS detection performance with automated transcription and segmentation methods is comparable to human-segmented and manually transcribed data; however, we find the automated segmentation methods reduces the number of utterances by 26.5%, impacting the the granularity of the data. We discuss the implications for developing AI-driven tools that support collaborative learning in classrooms.
title Dude, where's my utterance? Evaluating the effects of automatic segmentation and transcription on CPS detection
topic Human-Computer Interaction
Computation and Language
Computers and Society
Audio and Speech Processing
url https://arxiv.org/abs/2507.04454