Année : 2019
Lieu de publication de l'article :
Résumé de l'article
Virtual humans are frequently used to help medical students prac-tice communication skills. Here, we show that communication skillsfeatures drawn from the literature on best practices for doctor-patient communication can be used to predict student interviewers’success in a given domain skill. We also demonstrate the viabilityof Bayesian Rule Lists, an interpretable machine learning model,for this use case. Bayesian Rule Lists’ predictive performance iscomparable to that of other other commonly used algorithms, in-cluding decision trees. This suggests that Bayesian Rule Lists, whichproduce simple, human-readable trained binary classifiers, may besuitable for providing feedback for educational purposes.CCS CONCEPTS•Human-centered computing→HCI design and evaluationmethods; Natural language interfaces; Virtual reality; • Ap-plied computing→ Interactive learning environments; Computer-assisted instruction; •Computingmethodologies→Natural lan-guage processing; Supervised learning by classification.KEYWORDScommunications skills learning; virtual humans; doctor-patientcommunication; interpretable machine learningACM Reference Format:Stephanie Carnell, Benjamin Lok, Melva T. James, and Jonathan K. Su. 2019.Predicting Student Success in Communication Skills Learning Scenarioswith Virtual Humans. In The 9th International Learning Analytics & Knowl-edge Conference (LAK19), March 4–8, 2019, Tempe, AZ, USA. ACM, New York,NY, USA, 5 pages. https://doi.org/10.1145/3303772.3303828
Mots-clés
Best practice,Machine learning,Algorithm,humans,Decision tree,Human-readable medium,Rule 90, virtual humans, communication skills,
Français
English
