Analysis of Semantic Content and Its Relation to Team Neurophysiology during Submarine Crew Training

Abstract

A multi-level framework for analyzing team cognition based on team communication content and team neurophysiology is described. The semantic content of team communication in submarine training crews is quantified using Latent Semantic Analysis (LSA), and their team neurophysiology is quantified using the previously described neurophysiologic synchrony method. In the current study, we validate the LSA communication metrics by demonstrating their sensitivity to variations in training segment and by showing that less experienced (novice) crews can be differentiated from more experienced crews based on the semantic relatedness of their communications. Cross-correlations between an LSA metric and a team neurophysiology metric are explored to examine fluctuations in the lead-lag relationship between team communication and team neurophysiology as a function of training segment and level of team experience. Finally, the implications of this research for team training and assessment are considered.

Toward a quantitative description of the neurodynamic organizations of teams

“…Here the navigation simulations were divided into Briefing, Simulation, and Debriefing segments, i.e., the context of the task was changed by the training protocol. Much like we have seen with the drawing difficulties of MT teams, each of these simulation segments was characterized by different NS distributions reflecting different organizational states of the teams and these changes could be related to other measures like conversation and spatial proximity (Gorman, Martin, Dunbar, Galloway, & Stevens, 2013). The team neurodynamic modeling systems also rapidly detected periods of team uncertainty or stress on the navigation simulations and quantitatively distinguished the performances of expert submarine navigation teams and Junior Officers in training .…”

Advancing the Science of Collaborative Problem Solving

“…The technique analyzes meaning rather than merely the words explicitly used, so it can account for variability in how different people express similar events or situations in collaborative situations. The approach has been applied to analyze communication across a range of complex collaborative tasks and has been shown to be able to classify interaction types (Gorman, Martin, Dunbar, Stevens, & Galloway, 2013), predict overall scores of individuals and teams (Martin & Foltz, 2004), and alert instructors when students are drifting from effective collaboration patterns (Foltz & Martin, 2008). Dowell et al (2018) successfully used LSA to analyze teammates on the basis of their interaction profiles, which had six measures derived from the flow of conversation in natural language: participation, social impact on others, responsivity to others, internal cohesion within a speaker, the newness of information to the conversation, and the density of content.…”

Cross-Level Effects Between Neurophysiology and Communication During Team Training

“…Preliminary findings of this research were reported at the 2013 Human–Computer Interaction international conference (Gorman, Martin, Dunbar, Stevens, & Galloway, 2013). This research was supported by Defense Advanced Projects Agency Contract W31P4Q-12-C-0166 and National Science Foundation SBIR Grant IIP 121215327.…”