Social Science for Natural Language Processing: A Hostile Narrative Analysis Prototype

We propose a new methodology for analysing hostile narratives by incorporating theories from Social Science into a Natural Language Processing (NLP) pipeline. Drawing upon Peace Research, we use the "Self-Other gradient" from the theory of cultural violence to develop a framework and methodology for analysing hostile narratives. As test data for this development, we contrast Hitler's Mein Kampf and texts from the "War on Terror" era with non-violent speeches from Martin Luther King. Our experiments with this dataset question the explanatory value of numerical outputs generated by quantitative methods in NLP. In response, we draw upon narrative analysis techniques for the technical development of our pipeline. We experimentally show how analysing narrative clauses has the potential to generate outputs of improved explanatory value to quantitative methods. To the best of our knowledge, this work constitutes the first attempt to incorporate cultural violence into an NLP pipeline for the analysis of hostile narratives.