Using machine learning and topic modeling to examine manifestos of violent attackers
New peer-reviewed academic study using machine learning and topic modeling to examine manifestos of violent attackers
Citation
Petreca, V. G., Burgess, A. A., Wise, J., & Burgess, A. W. (2025). Using machine learning and topic modeling to examine manifestos of violent attackers. Journal of Threat Assessment and Management, 12(2), 132–148. https://doi.org/10.1037/tam0000232
Abstract
This study is a linguistic analysis of 23 published manifestos written by violent offenders who committed or threatened a targeted attack. The acts of violence were primarily motivated by an ideology or a personal grievance that occurred between 1974 and 2022. The aim of the study was to examine if machine learning and the application of BERTopic was useful in forensic linguistics as it is applied to threat and risk assessment. We tested different parameter values of the techniques. Findings identified an informational table containing topic number and count, local and general topics by contrasting different settings (15 neighbors to 100 neighbors) associated with ideology, grievances, direct threats of violence, and other general topics. The semantic meaning behind planning stages, hierarchical clustering, and a heatmap of the similarity matrix showing relationships between topic shared and/or overlaps are depicted and discussed. (PsycInfo Database Record (c) 2025 APA, all rights reserved)
Impact Statement
Unsupervised topic modeling may be a valuable technique or tool in identifying signs and patterns of threat in large volumes of text. The main finding that a machine learning technique can be used to screen and minimize bias in the assessment of written materials, revealing both explicit and implicit themes that may be critical in evaluations, supports the utility of such strategies in forensic linguistics and bolstering threat assessment processes. (PsycInfo Database Record (c) 2025 APA, all rights reserved)
Copyright
Holder: American Psychological Association
Year: 2024
More information on the CEMIR’s Substack for BTAMs and K12 school safety is available to paid subscribers.
An Introduction to Comprehensive Emergency Management for K12 Schools
Overview video of how Emergency Management should be applied to the ‘before, during, and after’ for school safety - from an all-hazards, all-threats perspective.