Students, Teachers, Exams and MOOCs: Predicting and Optimizing Attainment in Web-Based Education Using a Probabilistic Graphical Model

  • Bar Shalem
  • Yoram Bachrach
  • John Guiver
  • Christopher M. Bishop
Conference paper

DOI: 10.1007/978-3-662-44845-8_6

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8726)
Cite this paper as:
Shalem B., Bachrach Y., Guiver J., Bishop C.M. (2014) Students, Teachers, Exams and MOOCs: Predicting and Optimizing Attainment in Web-Based Education Using a Probabilistic Graphical Model. In: Calders T., Esposito F., Hüllermeier E., Meo R. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2014. Lecture Notes in Computer Science, vol 8726. Springer, Berlin, Heidelberg

Abstract

We propose a probabilistic graphical model for predicting student attainment in web-based education. We empirically evaluate our model on a crowdsourced dataset with students and teachers; Teachers prepared lessons on various topics. Students read lessons by various teachers and then solved a multiple choice exam. Our model gets input data regarding past interactions between students and teachers and past student attainment. It then estimates abilities of students, competence of teachers and difficulty of questions, and predicts future student outcomes. We show that our model’s predictions are more accurate than heuristic approaches. We also show how demographic profiles and personality traits correlate with student performance in this task. Finally, given a limited pool of teachers, we propose an approach for using information from our model to maximize the number of students passing an exam of a given difficulty, by optimally assigning teachers to students. We evaluate the potential impact of our optimization approach using a simulation based on our dataset, showing an improvement in the overall performance.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Bar Shalem
    • 1
  • Yoram Bachrach
    • 2
  • John Guiver
    • 2
  • Christopher M. Bishop
    • 2
  1. 1.Bar-Ilan UniversityRamat GanIsrael
  2. 2.Microsoft ResearchCambridgeUK

Personalised recommendations