Predicting Student Success in Communication Skills Learning Scenarios with Virtual Humans

  title={Predicting Student Success in Communication Skills Learning Scenarios with Virtual Humans},
  author={Stephanie Carnell and Benjamin C. Lok and Melva T. James and Jonathan Su},
  journal={Proceedings of the 9th International Conference on Learning Analytics \& Knowledge},
Virtual humans are frequently used to help medical students practice communication skills. Here, we show that communication skills features 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 viability of Bayesian Rule Lists, an interpretable machine learning model, for this use case. Bayesian Rule Lists' predictive performance is comparable to that of other other… 

Figures and Tables from this paper

Predictive Analysis Tool for Predicting Student Performance and Placement Performance using ML algorithms.
The aim is to develop a training model that predicts the final CGPA of a student and also the placement result of the particular student, and to predict the results using algorithms like Linear Regression, Decision tree algorithm, K-nearest neighbor algorithm, Logistical regression, and Lasso regression algorithm.
Patient-Provider Communication Training Models for Interactive Speech Devices
This study proposes designing an ontology-based interaction model that can direct software agents to train dental and medical students and created two instance-based models from the ontology to test the operational execution of the model using a prototype software engine.
Designing a Virtual Client for Requirements Elicitation Interviews
VIrtual CustOmer (VICO), an intent-based, multimodal, conversational agent, which offers an interview experience comparable to talking to a human and provides a transcript of the interview annotated with the mistakes students made in it is proposed.
Computer-Controlled Virtual Humans in Patient-Facing Systems: Systematic Review and Meta-Analysis
Evidence for the efficacy of VH in patient-facing systems is offered and future studies also need to identify what features of virtual human interventions contribute toward their effectiveness.
An Active Data Representation of Videos for Automatic Scoring of Oral Presentation Delivery Skills and Feedback Generation
An automatic scoring system for presentation delivery skills using a novel active data representation method to automatically rate segments of a full video presentation that does not require event detectors is proposed.
Computer-Controlled Virtual Humans in Patient-Facing Systems: Systematic Review and Meta-Analysis (Preprint)
This review offers evidence for the efficacy of VH in patient-facing systems and identifies two distinct design categories — simple VH and VH augmented with health sensors and trackers.
Investigation of the effect of communicational empowerment pattern on nursing student's communicational competency
  • A. Salar
  • Education, Medicine
    Journal of education and health promotion
  • 2019
Using the communicational empowerment method in clinical education is possible and it increases the Communicational competency among senior nursing students.
The Impact of Virtual Reality in the Social Presence of a Virtual Agent
Results indicate that participant perception of social presence of virtual characters is higher in VR, a stronger impact compared to the same interaction in a traditional non-immersive platform, both in terms of presence and believability.
Embodied Multimodal Agents to Bridge the Understanding Gap
It is proposed that embodied multimodal agents, i.e., avatars, provide additional structure that can be used to train models that move NLP systems closer to genuine “understanding” of grounded language.
User-Aware Shared Perception for Embodied Agents
Diana is presented, an embodied agent who is aware of her own virtual space and the physical space around her and begins to develop the conceit that the user is interacting with a peer rather than a program.


Using Learning Analytics to Identify Medical Student Misconceptions in an Online Virtual Patient Environment.
These findings serve to inform the design of an adaptive system that tailors the delivery of formative feedback to promote better learning outcomes in the domain of clinical reasoning.
Adapting Virtual Patient Interviews for Interviewing Skills Training of Novice Healthcare Students
A method for identifying topics about which novices are likely to ask by reviewing previous transcripts of novice interactions is outlined, and results indicate that the method was successful in such identification.
A crowdsourcing method to develop virtual human conversational agents
AI in Education needs interpretable machine learning: Lessons from Open Learner Modelling
It is argued that this work can provide a valuable starting point for a framework of interpretable AI, and is of relevance to the application of both knowledge-based and machine learning systems in other high-stakes contexts, beyond education.
The use of virtual patients to teach medical students history taking and communication skills.
Understanding empathy training with virtual patients
High Score! - Motivation Strategies for User Participation in Virtual Human Development
The use of leaderboards, narratives and deadlines are proposed as motivation strategies to persuade user participation in the conversational modeling for virtual humans for medical students through a user study conducted with medical students.
The RAP system: automatic feedback of oral presentation skills using multimodal analysis and low-cost sensors
RAP is presented, a scalable system to provide automatic feedback to entry-level students to develop basic oral presentation skills by analyzing posture, gaze, volume, filled pauses and the slides of the presenters through data captured by very low-cost sensors.
Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
A generative model called Bayesian Rule Lists is introduced that yields a posterior distribution over possible decision lists that employs a novel prior structure to encourage sparsity and has predictive accuracy on par with the current top algorithms for prediction in machine learning.