Authorship Analysis of Inspire Magazine through Stylometric and Psychological Features

When we read a piece of writing, the meaning we derive from that text often includes information about the authors themselves. Clues to their identity, worldview, and even psychological states are encoded in features such as word choice and sentence structure. This work describes how writing style features can be used to analyze the authorship of extreme jihadist writing. Inspire magazine is an online, English-language magazine published by Al-Qaeda in the Arabian Peninsula. Our work has revealed similarities and disparities in the writing styles of Inspire authors using features such as word choice and sentence structure, as well as semantic and psychological features. The Linguistic Inquiry and Word Count (LIWC) resource is a lexicon that identifies words and phrases associated with a set of cognitive processes and psychological states [1]. LIWC was originally developed to determine the psychological properties of English text but has since been expanded to other languages, including Arabic. Prior to this work, the Arabic-language version of LIWC was limited to a small category of function words and did not have the full analytical power of the English-language version. We show how a method of lexicon expansion, translation, and assessment by a native Arabic speaker was used to produce a more robust Arabic-language version of the resource and is applied to the psychological analysis of Inspire content in both English and Arabic.