Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Borchers, Conrad, Švábenský, Valdemar, Kafle, Sandesh K., Tang, Kevin K., Vykopal, Jan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914431768723456
author Borchers, Conrad
Švábenský, Valdemar
Kafle, Sandesh K.
Tang, Kevin K.
Vykopal, Jan
author_facet Borchers, Conrad
Švábenský, Valdemar
Kafle, Sandesh K.
Tang, Kevin K.
Vykopal, Jan
contents Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23 teams (76 students) across five exercise sessions. Study 1 codes objectives and team emails with Bloom's taxonomy and models the completion of key exercise tasks with generalized linear mixed models. Alignment, defined as the discrepancy between required and enacted Bloom levels, predicts success, whereas the Bloom category alone does not predict success once discrepancy is considered. Study 2 compares predictive feature families using grouped cross-validation and l1-regularized logistic regression. Text embeddings and log features outperform Bloom-only models (AUC~0.74 and 0.71 vs. 0.55), and their combination performs best (Test AUC~0.80), with Bloom frequencies adding little. Overall, the work offers a measure of alignment for simulations and shows that multimodal traces best forecast performance, while alignment provides interpretable diagnostic insight.
format Preprint
id arxiv_https___arxiv_org_abs_2603_28553
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?
Borchers, Conrad
Švábenský, Valdemar
Kafle, Sandesh K.
Tang, Kevin K.
Vykopal, Jan
Human-Computer Interaction
Computers and Society
Machine Learning
Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23 teams (76 students) across five exercise sessions. Study 1 codes objectives and team emails with Bloom's taxonomy and models the completion of key exercise tasks with generalized linear mixed models. Alignment, defined as the discrepancy between required and enacted Bloom levels, predicts success, whereas the Bloom category alone does not predict success once discrepancy is considered. Study 2 compares predictive feature families using grouped cross-validation and l1-regularized logistic regression. Text embeddings and log features outperform Bloom-only models (AUC~0.74 and 0.71 vs. 0.55), and their combination performs best (Test AUC~0.80), with Bloom frequencies adding little. Overall, the work offers a measure of alignment for simulations and shows that multimodal traces best forecast performance, while alignment provides interpretable diagnostic insight.
title Multimodal Analytics of Cybersecurity Crisis Preparation Exercises: What Predicts Success?
topic Human-Computer Interaction
Computers and Society
Machine Learning
url https://arxiv.org/abs/2603.28553