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

doi:10.1145/3583780.3615143

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

^*Corresponding author for this work

Department of Data Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-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. © 2023 Copyright held by the owner/author(s).

Original language	English
Title of host publication	CIKM ’23
Subtitle of host publication	Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
Publisher	Association for Computing Machinery
Pages	3798-3802
ISBN (Print)	9798400701245
DOIs	https://doi.org/10.1145/3583780.3615143
Publication status	Published - 2023
Event	32nd ACM International Conference on Information and Knowledge Management (CIKM 2023) - University of Birmingham and Eastside Rooms, Birmingham, United Kingdom Duration: 21 Oct 2023 → 25 Oct 2023 https://uobevents.eventsair.com/cikm2023/ https://uobevents.eventsair.com/cikm2023/accepted-papers https://dl.acm.org/doi/proceedings/10.1145/3583780

Publication series

Name	International Conference on Information and Knowledge Management, Proceedings

Conference

Conference	32nd ACM International Conference on Information and Knowledge Management (CIKM 2023)
Abbreviated title	CIKM ’23
Place	United Kingdom
City	Birmingham
Period	21/10/23 → 25/10/23
Internet address	https://uobevents.eventsair.com/cikm2023/ https://uobevents.eventsair.com/cikm2023/accepted-papers https://dl.acm.org/doi/proceedings/10.1145/3583780

Research Keywords

AI in education
assessment
classroom dialogue
student modeling

Access Output

10.1145/3583780.3615143

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Chen, J., Liu, Z., Huang, S., Huang, Y., Zhao, X., Gao, B., & Luo, W. (2023). Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue. In CIKM ’23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (pp. 3798-3802). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3583780.3615143

Chen, Jiahao ; Liu, Zitao ; Huang, Shuyan et al. / Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue. CIKM ’23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2023. pp. 3798-3802 (International Conference on Information and Knowledge Management, Proceedings).

@inproceedings{2e371d1e4e1d48249b339827d8560f85,

title = "Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue",

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. {\textcopyright} 2023 Copyright held by the owner/author(s).",

keywords = "AI in education, assessment, classroom dialogue, student modeling",

author = "Jiahao Chen and Zitao Liu and Shuyan Huang and Yaying Huang and Xiangyu Zhao and Boyu Gao and Weiqi Luo",

year = "2023",

doi = "10.1145/3583780.3615143",

language = "English",

isbn = "9798400701245",

series = "International Conference on Information and Knowledge Management, Proceedings",

publisher = "Association for Computing Machinery",

pages = "3798--3802",

booktitle = "CIKM {\textquoteright}23",

address = "United States",

note = "32nd ACM International Conference on Information and Knowledge Management (CIKM 2023), CIKM {\textquoteright}23 ; Conference date: 21-10-2023 Through 25-10-2023",

url = "https://uobevents.eventsair.com/cikm2023/, https://uobevents.eventsair.com/cikm2023/accepted-papers, https://dl.acm.org/doi/proceedings/10.1145/3583780",

}

Chen, J, Liu, Z, Huang, S, Huang, Y, Zhao, X, Gao, B & Luo, W 2023, Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue. in CIKM ’23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 3798-3802, 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023), Birmingham, United Kingdom, 21/10/23. https://doi.org/10.1145/3583780.3615143

Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue. / Chen, Jiahao; Liu, Zitao; Huang, Shuyan et al.
CIKM ’23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2023. p. 3798-3802 (International Conference on Information and Knowledge Management, Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue

AU - Chen, Jiahao

AU - Liu, Zitao

AU - Huang, Shuyan

AU - Huang, Yaying

AU - Zhao, Xiangyu

AU - Gao, Boyu

AU - Luo, Weiqi

PY - 2023

Y1 - 2023

N2 - 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. © 2023 Copyright held by the owner/author(s).

AB - 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. © 2023 Copyright held by the owner/author(s).

KW - AI in education

KW - assessment

KW - classroom dialogue

KW - student modeling

UR - https://www.scopus.com/pages/publications/85178117821

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85178117821&origin=recordpage

U2 - 10.1145/3583780.3615143

DO - 10.1145/3583780.3615143

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798400701245

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 3798

EP - 3802

BT - CIKM ’23

PB - Association for Computing Machinery

T2 - 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023)

Y2 - 21 October 2023 through 25 October 2023

ER -

Chen J, Liu Z, Huang S, Huang Y, Zhao X, Gao B et al. Assessing Student Performance with Multi-granularity Attention from Online Classroom Dialogue. In CIKM ’23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2023. p. 3798-3802. (International Conference on Information and Knowledge Management, Proceedings). Epub 2023 Oct 21. doi: 10.1145/3583780.3615143

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

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this