Applying Discourse Analysis and Data Mining Methods to Spoken OSCE Assessments

This paper looks at the transcribed data of patient-doctor consultations in an examination setting. The doctors are internationally qualified and enrolled in a bridging course as preparation for their Australian Medical Council examination. In this study, we attempt to ascertain if there are measurable linguistic features of the consultations, and to investigate whether there is any relevant information about the communicative styles of the qualifying doctors that may predict satisfactory or non-satisfactory examination outcomes. We have taken a discourse analysis approach in this study, where the core unit of analysis is a `turn'. We approach this problem as a binary classification task and employ data mining methods to see whether the application of which to richly annotated dialogues can produce a system with an adequate predictive capacity.

• Type: Conference
• Year: 2008
• Where: COLING
• Authors: Meladel Mistica, Timothy Baldwin, Marisa Cordella, Simon Musgrave
• Keywords: COLING 2008, Computational Linguistics, Examination Setting, Measurable Linguistic Features, Medical Council Examination