A Bootstrapped Model to Detect Abuse and Intent in White Supremacist Corpora
This addresses the challenge for intelligence analysts in identifying violent intent in white supremacist content, though it is incremental as it builds on existing methods for abuse detection.
The paper tackles the problem of distinguishing extremist rhetoric from potential violence by building a predictive model for intent, bootstrapping from seed words and templates, and merging it with abuse detection to identify posts indicating violent desire. It validates the model with crowd-sourced labeling, achieving stable predictions in a few rounds.
Intelligence analysts face a difficult problem: distinguishing extremist rhetoric from potential extremist violence. Many are content to express abuse against some target group, but only a few indicate a willingness to engage in violence. We address this problem by building a predictive model for intent, bootstrapping from a seed set of intent words, and language templates expressing intent. We design both an n-gram and attention-based deep learner for intent and use them as colearners to improve both the basis for prediction and the predictions themselves. They converge to stable predictions in a few rounds. We merge predictions of intent with predictions of abusive language to detect posts that indicate a desire for violent action. We validate the predictions by comparing them to crowd-sourced labelling. The methodology can be applied to other linguistic properties for which a plausible starting point can be defined.