Mining case summaries in BioWorld
Eric Poitras, Tenzin Doleck, Susanne P. Lajoie · 2014
BioWorld is a computer-based learning environment that was designed to support novices in diagnosing medical diseases. In this study, we examine case summaries written in BioWorld. We explore the use of text classification techniques to mine case summaries written in BioWorld. In particular, we evaluate the accuracy of several text classification algorithms in Diagnosis Correctness and Novice-Expert Overlay Model (i.e., recognizing case summaries written by novice and expert physicians). Experimental results suggest that text classification is a promising approach for mining case summaries.