Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

The Stylometric Processing of Sensory Open Source Data

Loading...
Thumbnail Image

Date

Authors

Kernot, David

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

This research project’s end goal is on the Lone Wolf Terrorist. The project uses an exploratory approach to the self-radicalisation problem by creating a stylistic fingerprint of a person's personality, or self, from subtle characteristics hidden in a person's writing style. It separates the identity of one person from another based on their writing style. It also separates the writings of suicide attackers from ‘normal' bloggers by critical slowing down; a dynamical property used to develop early warning signs of tipping points. It identifies changes in a person's moods, or shifts from one state to another, that might indicate a tipping point for self-radicalisation. Research into authorship identity using personality is a relatively new area in the field of neurolinguistics. There are very few methods that model how an individual's cognitive functions present themselves in writing. Here, we develop a novel algorithm, RPAS, which draws on cognitive functions such as aging, sensory processing, abstract or concrete thinking through referential activity emotional experiences, and a person's internal gender for identity. We use well-known techniques such as Principal Component Analysis, Linear Discriminant Analysis, and the Vector Space Method to cluster multiple anonymous-authored works. Here we use a new approach, using seriation with noise to separate subtle features in individuals. We conduct time series analysis using modified variants of 1-lag autocorrelation and the coefficient of skewness, two statistical metrics that change near a tipping point, to track serious life events in an individual through cognitive linguistic markers. In our journey of discovery, we uncover secrets about the Elizabethan playwrights hidden for over 400 years. We uncover markers for depression and anxiety in modern-day writers and identify linguistic cues for Alzheimer's disease much earlier than other studies using sensory processing. In using these techniques on the Lone Wolf, we can separate their writing style used before their attacks that differs from other writing.

Description

Citation

Source

Book Title

Entity type

Access Statement

License Rights

Restricted until

Downloads

abcd