Skip to main navigation Skip to search Skip to main content

Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue

  • Jiahao Chen
  • , Zitao Liu
  • , Shuyan Huang
  • , Yaying Huang
  • , Xiangyu Zhao
  • , Boyu Gao
  • , Weiqi Luo
  • TAL Education Group
  • Jinan University
  • City University of Hong Kong

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Accurately judging students' ongoing performance is very crucial for real-world educational scenarios. In this work, we focus on the task of automatically predicting students' levels of mastery of math questions from teacher-student classroom dialogue data in the online learning environment. We propose a novel neural network armed with a multi-granularity attention mechanism to capture the personalized pedagogical instructions from the very noisy teacher-student dialogue transcriptions. We conduct experiments on a real-world educational dataset and the results demonstrate the superiority and availability of our model in terms of various evaluation metrics.

Original languageEnglish
Title of host publicationCIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages3798-3802
Number of pages5
ISBN (Electronic)9798400701245
DOIs
StatePublished - 21 Oct 2023
Externally publishedYes
Event32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, United Kingdom
Duration: 21 Oct 202325 Oct 2023

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
Country/TerritoryUnited Kingdom
CityBirmingham
Period21/10/2325/10/23

Keywords

  • AI in education
  • assessment
  • classroom dialogue
  • student modeling

Fingerprint

Dive into the research topics of 'Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue'. Together they form a unique fingerprint.

Cite this