Course-Graph Discovery from Academic Performance Using Nonnegative LassoNet

Mengfei Liu, Shuangshuang Wei, Shuhui Liu, Xuequn Shang, Yupei Zhang

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

Abstract

This paper focuses on the problem of mining a course graph from students’ academic grades in formal education, which is an essential topic for artificial intelligence in education (AIED). However, most current methods often suffer from hardly understanding associations in practice. To this end, we formulate this problem into a feature selection schema that the proposed nonnegative LassoNet can solve. In the study case, we use the course scores of 4,577 records in the computer science department at our university. From the study results, our method achieves about 78% accuracy in score prediction with an acceptable error, which is better than traditional regression models with shrinkage. Based on the sparse self-expressive representation, we create a course map to show the associations behind the student’s academic performance, providing pieces of evidence for education studies and triggering exciting discoveries.

Original languageEnglish
Title of host publicationComputer Science and Education. Educational Digitalization - 18th International Conference, ICCSE 2023, Proceedings
EditorsWenxing Hong, Geetha Kanaparan
PublisherSpringer Science and Business Media Deutschland GmbH
Pages364-370
Number of pages7
ISBN (Print)9789819707362
DOIs
StatePublished - 2024
Event18th International Conference on Computer Science and Education, ICCSE 2023 - Sepang, Malaysia
Duration: 1 Dec 20237 Dec 2023

Publication series

NameCommunications in Computer and Information Science
Volume2025 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference18th International Conference on Computer Science and Education, ICCSE 2023
Country/TerritoryMalaysia
CitySepang
Period1/12/237/12/23

Keywords

  • Academic performance prediction
  • Course-graph discovery
  • Nonnegative LassoNet
  • Self-expressive representation

Fingerprint

Dive into the research topics of 'Course-Graph Discovery from Academic Performance Using Nonnegative LassoNet'. Together they form a unique fingerprint.

Cite this