Stephen Anning | University of Southampton (original) (raw)

Papers by Stephen Anning

We propose a new methodology for analysing hostile narratives by incorporating theories from Soci... more 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.

Journal of intelligence, conflict and warfare, Jan 31, 2022

Journal of intelligence, conflict and warfare, Jan 31, 2023

14th ACM Web Science Conference 2022

The Journal of Intelligence, Conflict, and Warfare, 2022

On November 24, 2021, Mr. Stephen Anning presented on Operationalizing Human Security in Contempo... more On November 24, 2021, Mr. Stephen Anning presented on Operationalizing Human Security in Contemporary Operating Environment at the 2021 CASIS West Coast Security Conference. The key points of discussion included the concept of human security, the differences between interstate and intrastate conflict, the challenges of understanding human security, and how operationalizing human security can address some of those challenges. The presentation was followed by a question and answer period with questions from the audience and CASIS Vancouver executives.

This abstract proposes a talk about PhD research into developing an NLP pipeline for Conflict Nar... more This abstract proposes a talk about PhD research into developing an NLP pipeline for Conflict Narrative Detection. In response to increased incidences of online abuse, a new industry of hate speech detection using NLP has emerged. Accordingly, we tested NLP technologies used by this industry to discover how quantitatively analysing language distorts meaning. We compiled a dataset comprising "Mein Kampf" from Hitler, "War on Terror" texts from George Bush and Osama bin Laden, and in how he advocated for non-violence, speeches from Martin Luther King provide control data. We tested both general-purpose and state-of-the-art sentiment analysis technologies from TextBlob, Google and IBM. Where distinctive results would be expected from a dataset of extremes, our tests show that regardless of technical sophistication, these technologies are unable to distinguish abusive from non-abusive texts. We address this problem with quantitatively analysing language by offering C...

The US Army War College Quarterly: Parameters, 2012

The Journal of Intelligence, Conflict, and Warfare, 2022

Drawing upon primary research funded by the UK Defence and Security Accelerator (DASA), this arti... more Drawing upon primary research funded by the UK Defence and Security Accelerator (DASA), this article is about using data analytics and artificial intelligence (AI) for operationalising human security in the contemporary operating environment. The idea of human security has gained much traction in the international community since its introduction in a 1994 United Nations Development Programme (UNDP) report and has more recently become a military concern. Yet, the core tenets of this idea remain contested, and the military role in support of human security remains an open question. Nonetheless, the concurrent increase in Open Data and AI does give rise to new opportunities to understand the various human security concerns. In response, DASA funded Projects SOLEBAY and HAMOC to research these concerns and the possibilities of data analytics for human security. Drawing on the research findings, we propose the idea of Population Intelligence (POPINT) as a new intelligence discipline to ...

13th ACM Web Science Conference 2021

We propose a new methodology for analysing hostile narratives by incorporating theories from Soci... more 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.

Human Trafficking in Conflict

We propose a new methodology for analysing hostile narratives by incorporating theories from Soci... more 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.

Journal of intelligence, conflict and warfare, Jan 31, 2022

Journal of intelligence, conflict and warfare, Jan 31, 2023

14th ACM Web Science Conference 2022

The Journal of Intelligence, Conflict, and Warfare, 2022

On November 24, 2021, Mr. Stephen Anning presented on Operationalizing Human Security in Contempo... more On November 24, 2021, Mr. Stephen Anning presented on Operationalizing Human Security in Contemporary Operating Environment at the 2021 CASIS West Coast Security Conference. The key points of discussion included the concept of human security, the differences between interstate and intrastate conflict, the challenges of understanding human security, and how operationalizing human security can address some of those challenges. The presentation was followed by a question and answer period with questions from the audience and CASIS Vancouver executives.

This abstract proposes a talk about PhD research into developing an NLP pipeline for Conflict Nar... more This abstract proposes a talk about PhD research into developing an NLP pipeline for Conflict Narrative Detection. In response to increased incidences of online abuse, a new industry of hate speech detection using NLP has emerged. Accordingly, we tested NLP technologies used by this industry to discover how quantitatively analysing language distorts meaning. We compiled a dataset comprising "Mein Kampf" from Hitler, "War on Terror" texts from George Bush and Osama bin Laden, and in how he advocated for non-violence, speeches from Martin Luther King provide control data. We tested both general-purpose and state-of-the-art sentiment analysis technologies from TextBlob, Google and IBM. Where distinctive results would be expected from a dataset of extremes, our tests show that regardless of technical sophistication, these technologies are unable to distinguish abusive from non-abusive texts. We address this problem with quantitatively analysing language by offering C...

The US Army War College Quarterly: Parameters, 2012

The Journal of Intelligence, Conflict, and Warfare, 2022

Drawing upon primary research funded by the UK Defence and Security Accelerator (DASA), this arti... more Drawing upon primary research funded by the UK Defence and Security Accelerator (DASA), this article is about using data analytics and artificial intelligence (AI) for operationalising human security in the contemporary operating environment. The idea of human security has gained much traction in the international community since its introduction in a 1994 United Nations Development Programme (UNDP) report and has more recently become a military concern. Yet, the core tenets of this idea remain contested, and the military role in support of human security remains an open question. Nonetheless, the concurrent increase in Open Data and AI does give rise to new opportunities to understand the various human security concerns. In response, DASA funded Projects SOLEBAY and HAMOC to research these concerns and the possibilities of data analytics for human security. Drawing on the research findings, we propose the idea of Population Intelligence (POPINT) as a new intelligence discipline to ...

13th ACM Web Science Conference 2021

We propose a new methodology for analysing hostile narratives by incorporating theories from Soci... more 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.

Human Trafficking in Conflict