Search

1) Help novice students scaffold problem-solving, engage safely in the deliberate practice of diagnostic reasoning and medical decision-making in real-time; 2) Assess how accurately students gather and apply data in medical reasoning and treatment during High Fidelity Patient Simulations (HFPS); 3) Identify students scientific misconceptions related to the case; 4) Promote student metacognitive processing, self-assessment and self-efficacy; 5) Facilitate the explicit calibration of student confidence in deliberate reasoning with patient outcomes.Mixed method; metacognitive calibration self-assessing (MCC) survey tool applied to HFPS; N=80, 20 teams of 6 medical students; Semi-structured interviews with faculty N=5.When scored by faculty using a rubric, the mean student accuracy ranged from 23-74%, whereas their self-assessment of confidence ranged from 71-86%. This result revealed overconfidence bias in novice students regarding the correctness of their wrong responses. The most common misconception identified was inverting cause and effect: metabolic acidosis was pointed to as the cause of the patient's problems, rather than a consequence of untreated diabetes mellitus. The most common treatment error was overtreatment, with unnecessary added medication. Interviews with faculty suggested the MCC tool improved the team process by slowing students down, requiring them to think through their answers, and that overall, the tool improved their critical thinking.This study demonstrated the feasibility of using a metacognitive confidence calibration tool to assist students in learning to make deliberate diagnostic reasoning and on patient care in real-time during simulations while observing objectively their levels of psychological confidence against patient outcomes.

Current approaches to player profiling are limited in that they typically employ only a single one of numerous of available techniques shown to have utility for categorizing and explaining player behavior. We propose a more comprehensive Video Game Player Profile Framework that considers the demographic, psychographic, mental model, and behavioral modeling approaches shown to be effective for describing gamer populations. We suggest that our proposed approach can improve the efficacy of video game player profiles by grounding data-driven techniques in game analytics with the theoretical backing of demographic, psychometric, and psychographic measurements. We provide an overview of our proposed framework, discuss the usage and relevance of each component technique, and provide a proof-of-concept demonstration with archived data.

Technological advances have led to a rapid increase in the implementation of virtual reality (VR) across multiple sectors of society. Further, we are seeing more researchers explore how the technology can be used to promote learning and training in a variety of domains. But there is a problematic gap between development of VR for training and education and learning theory to ensure its efficacy. We address this need by providing a theoretical lens through which to evaluate existing research in VR. We consider technology developments that have made VR more sophisticated and draw from research in the learning and cognitive sciences to evaluate their utility as learning affordances. With this, we examine existing research as a way to illustrate the practical value of theoretical evaluation. We conclude with a discussion how this theoretical framing can point the way for both better designed studies to accelerate learning and training as well as for more innovative adaptations for accelerating learning in immersive virtual reality.

Artificial intelligence has been developed to perform all manner of tasks but has not gained capabilities to support social cognition. We suggest that teams comprised of both humans and artificially intelligent agents cannot achieve optimal team performance unless all teammates have the capacity to employ social-cognitive mechanisms. These form the foundation for generating inferences about their counterparts and enable execution of informed, appropriate behaviors. Social intelligence and its utilization are known to be vital components of human-human teaming processes due to their importance in guiding the recognition, interpretation, and use of the signals that humans naturally use to shape their exchanges. Although modern sensors and algorithms could allow AI to observe most social cues, signals, and other indicators, the approximation of human-to-human social interaction -based upon aggregation and modeling of such cues is currently beyond the capacity of potential AI teammates. Partially, this is because humans are notoriously variable. We describe an approach for measuring social-cognitive features to produce the raw information needed to create human agent profiles that can be operated upon by artificial intelligences.

Research and development in virtual reality (VR) continues to influence all sectors of society. This has been particularly the case in the application of VR for learning and training. Due to the affordability of VR, it increasingly is providing a safe and cost-effective technology for studying learning and training. In this paper, we summarize findings from recent compilations of research in virtual reality that examined VR and learning. From this, we identify a set of recommendations distilled from these reviews in order to help the training research community structure their research based upon the extent empirical base. Our goal is to help the training community more effectively explore VR as a technology for learning.

This panel will provide a transdisciplinary perspective on developing artificial social intelligence for teams. A panel with representatives from the cognitive, computational, and neural sciences will discuss theoretical, methodological, and technological insights derived from their respective disciplines. These perspectives will be integrated via a set of questions meant to guide synthesis across disciplines in support of a transdisciplinary team research approach. Through discussion across the panel and audience, our goal is to contribute to research and development in the area of Human-AI-Robot Teaming effectiveness.

A significant challenge for the development of artificial social intelligence for effective human-machine teams is defining the forms of artificial knowledge structures needed for machine agents to meaningfully engage in collaboration. Relevant to this, individual and shared knowledge structure concepts have been proposed across a variety of disciplines, resulting in a lack of conceptual clarity and impeding their operationalization for human-machine teaming. To reconcile conceptual differences across disciplines and enable the emergence of complex socio-cognitive abilities in machine agents, research is needed to integrate theory on the knowledge structures that underpin complex cognition. Toward this end, we survey research from the cognitive and computational sciences to develop a framework for the systematic application and evaluation of knowledge structure concepts for machine agents in teams. Our approach focuses on contextual factors, specifically the task environment structure and the situation temporality, that can help guide knowledge structure requirements for artificial social intelligence.

As the complexity of aircraft cockpit operations increases, training effectiveness must be improved, and learning accelerated. Virtual reality (VR) training is increasingly offered as a method for improving training efficacy given its ability to provide a rich sensory experience during learning. This paper describes a study examining how training efficacy can be improved by improving learning diagnostics. We study how varying forms of knowledge assessment are related to different types of task knowledge and task performance in a VR flight simulator. The data suggest that participants who demonstrated higher training comprehension, measured via diagnostic test questions, on conceptual (and to a lesser effect) declarative knowledge, also demonstrated superior knowledge transfer in the VR flight simulator. Findings are discussed in the context of improving cognitively diagnostic assessments that are better able to predict task performance and inform individually tailored training remediation.

The modern information environment provides an opportunity for cognitive engineering to inform the study of information operations, which involve strategic, often politically-motivated actions to manipulate a targeted audience. In this paper we integrate interdisciplinary theoretical concepts to provide a foundation for a model of persuasion in information operations. We identify sensemaking and framing as key processes and connect these to narrative and identity theories to illustrate how they can inform the study of the individual and the collective in modern sociotechnical systems. From this, we propose a model of narrative persuasion to guide research on social media information operations. Through this, we offer a set of research guidelines to demonstrate how this can serve as a foundation for empirical work blending quantitative and qualitative methods. In this way, we show how cognitive and computational sciences can be blended in support of fundamental and applied research in information operations.

In this study, we explore the future of work by examining differences in productivity when teams are composed of only humans or both humans and machine agents. Our objective was to characterize the similarities and differences between human and human-machine teams as they work to coordinate across their specialized roles. This form of research is increasingly important given that machine agents are becoming commonplace in sociotechnical systems and playing a more active role in collaborative work. One particular class of machine agents, bots, is being introduced to these systems to facilitate both taskwork and teamwork. We investigated the association between bots and productivity outcomes in open source software development through an analysis of hundreds of project teams. The presence of bots in teams was associated with higher levels of productivity and higher work centralization in addition to greater amounts of observed communication. The adoption of bots in software teams may have tradeoffs, in that doing so may increase productivity, but could also increase workload. We discuss the theoretical and practical implications of these findings for advancing human-machine teaming research.