Online Deep Knowledge Tracing

Wenxin Zhang, Yupei Zhang, Shuhui Liu, Xuequn Shang

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

2 Scopus citations

Abstract

This study focuses on solving the problem of knowledge tracing in a practical situation, where the responses from students come in a stream. Most current works of deep knowledge tracing are pursuing to integrate of more side information or data structure, but they often fail to make self-update in the dynamic learning situation. Towards this end, we here proposed an online deep knowledge tracing model, dubbed ODKT, by utilizing the online gradient descent algorithm to develop the traditional deep knowledge tracing (DKT) into online learning. Rather than learning a perfect model, the ODKT aims to train DKT in its using process step by step. Experiments were conducted on four public datasets for knowledge tracing. The results demonstrate that the ODKT model is effective and more suitable for practical applications.

Original languageEnglish
Title of host publicationProceedings - 22nd IEEE International Conference on Data Mining Workshops, ICDMW 2022
EditorsK. Selcuk Candan, Thang N. Dinh, My T. Thai, Takashi Washio
PublisherIEEE Computer Society
Pages292-297
Number of pages6
ISBN (Electronic)9798350346091
DOIs
StatePublished - 2022
Event22nd IEEE International Conference on Data Mining Workshops, ICDMW 2022 - Orlando, United States
Duration: 28 Nov 20221 Dec 2022

Publication series

NameIEEE International Conference on Data Mining Workshops, ICDMW
Volume2022-November
ISSN (Print)2375-9232
ISSN (Electronic)2375-9259

Conference

Conference22nd IEEE International Conference on Data Mining Workshops, ICDMW 2022
Country/TerritoryUnited States
CityOrlando
Period28/11/221/12/22

Keywords

  • Educational Data Mining
  • Intelligent Education
  • Knowledge Tracing
  • Online Machine Learning
  • RNN

Fingerprint

Dive into the research topics of 'Online Deep Knowledge Tracing'. Together they form a unique fingerprint.

Cite this