Share Paper: Assessing the Utility of Deep Learning: Using Learner-System Interaction Data from BioWorld

  1. Tenzin Doleck, University of Southern California, United States
  2. Eric Poitras, University of Utah, United States
  3. Susanne Lajoie, McGill University, United States

Abstract: In recent years, deep learning (LeCun, Bengio, & Hinton, 2015) has drawn interest in many fields. As optimism for deep learning grows, a better understanding of the efficacy of deep learning is imperative, especially in analyzing and making sense of educational data. This study addresses this issue by establishing a benchmark for a common prediction task – student proficiency in diagnosing patient diseases in a system called BioWorld (Lajoie, 2009). To do so, we compared deep learning to existing solutions, including traditional machine learning algorithms that are commonly used in educational data mining. The dataset consists of log interaction data ...