Early predictors of persistence and performance in online language courses

Hagit Gabbay, Anat Cohen, Eitan Festinger

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review


This study examines the relationship between online learning behavior and learning outcomes with the aim of identifying early predictors of learners' persistence and success. Research focused on the first learning units of online language courses in a developing country in order to provide teachers and administrators with a simple model for identifying at-risk students. Using data from 716 students enrolled in 24 English courses at a Peruvian university, learning analytics approach was applied, framed by the self-determination theory (SDT). Results suggest that unit completion rates and time spent on learning, which are both related to sense of autonomy, strongly predict persistence at the course mid-point. Moreover, the same variables can predict student persistence as early as unit three, providing even earlier indications for dropping out. Quiz score and midterm grade, which are related to the SDT competence construct, moderately predict achievement, defined as the final exam grade. Relatedness factors (emails and Facebook activity) were not found to be early predictors.

Original languageEnglish
Title of host publicationEarly Warning Systems and Targeted Interventions for Student Success in Online Courses
Number of pages18
ISBN (Electronic)9781799850755
StatePublished - 26 Jun 2020

All Science Journal Classification (ASJC) codes

  • Social Sciences(all)


Dive into the research topics of 'Early predictors of persistence and performance in online language courses'. Together they form a unique fingerprint.

Cite this