A nonlinear state space model for identifying at-risk students in open online courses

Feng Wang, Li CHEN

Research output: Contribution to conferencePaperpeer-review

22 Citations (Scopus)

Abstract

How to identify at-risk students in open online courses has received increasing attention, since the dropout rate is unexpectedly high. Most prior studies have focused on using machine learning techniques to predict student dropout based on features extracted from students’ learning activity logs. However, little work has viewed the dropout prediction problem as a sequence classification problem in the consideration that the dropout probability of a student at the current time step can be likely dependent on her/his engagement at the previous time step. Therefore, in this paper, we propose a nonlinear state space model to solve this problem. We show how students’ latent states at different time steps can be learned via this model, and demonstrate its outperforming prediction accuracy relative to related methods through experiment.

Original languageEnglish
Pages527-532
Number of pages6
Publication statusPublished - 2016
Event9th International Conference on Educational Data Mining, EDM 2016 - Raleigh, United States
Duration: 29 Jun 20162 Jul 2016

Conference

Conference9th International Conference on Educational Data Mining, EDM 2016
Country/TerritoryUnited States
CityRaleigh
Period29/06/162/07/16

Scopus Subject Areas

  • Computer Science Applications
  • Information Systems

User-Defined Keywords

  • At-risk students
  • Dropout prediction
  • Open online courses, nonlinear state space model

Fingerprint

Dive into the research topics of 'A nonlinear state space model for identifying at-risk students in open online courses'. Together they form a unique fingerprint.

Cite this