📝 Original Info
- Title: Computational International Relations: What Can Programming, Coding and Internet Research Do for the Discipline?
- ArXiv ID: 1803.00105
- Date: 2018-02-28
- Authors: H. Akin Unver
📝 Abstract
Computational Social Science emerged as a highly technical and popular discipline in the last few years, owing to the substantial advances in communication technology and daily production of vast quantities of personal data. As per capita data production significantly increased in the last decade, both in terms of its size, bytes, as well as its detail, heart rate monitors, Internet connected appliances, smartphones, social scientists ability to extract meaningful social, political and demographic information from digital data also increased. A vast methodological gap exists in computational international relations, or ComInt, which refers to the use of one or a combination of tools such as data mining, natural language processing, automated text analysis, web scraping, geospatial analysis and machine learning to provide larger and better organized data to test more advanced theories of IR. After providing an overview of the potentials of computational IR and how an IR scholar can establish technical proficiency in computer science, such as starting with Python, R, QGis, ArcGIS or Github, this paper will focus on some of the author's works in providing an idea for IR students on how to think about computational IR. The paper argues that computational methods transcend the methodological schism between qualitative and quantitative approaches and form a solid foundation for building truly multi method research design.
💡 Deep Analysis
Deep Dive into Computational International Relations: What Can Programming, Coding and Internet Research Do for the Discipline?.
Computational Social Science emerged as a highly technical and popular discipline in the last few years, owing to the substantial advances in communication technology and daily production of vast quantities of personal data. As per capita data production significantly increased in the last decade, both in terms of its size, bytes, as well as its detail, heart rate monitors, Internet connected appliances, smartphones, social scientists ability to extract meaningful social, political and demographic information from digital data also increased. A vast methodological gap exists in computational international relations, or ComInt, which refers to the use of one or a combination of tools such as data mining, natural language processing, automated text analysis, web scraping, geospatial analysis and machine learning to provide larger and better organized data to test more advanced theories of IR. After providing an overview of the potentials of computational IR and how an IR scholar can esta
📄 Full Content
Computational International Relations (ComInt1 ), introduced as a specific inquiry of research in this paper, derives from the Computational Social Science (ComSoc 2 ) revolution of the last decade. International relations (IR) literature has long trailed behind political science (PolSci) since the seminal Designing Social Inquiry 3 (DSI) by King, Keohane and Verba. Setting the quantitative bounds of the discipline despite its evolution over the years, DSI has established the methodological orthodoxy of both IR and PolSci, becoming the key text in almost all methods classes. The showdown of critical and supportive camps over DSI has continued well into today, setting the parameters of methodological polarization. The strong empiricism of regression and statistical modelling was challenged by the qualitative camp for a variety of reasons, including distortion of analytical focus 4 , manipulation of data 5 , and overall skepticism over how much mathematical validity can imply causality 6 . This long and seemingly unending core debate on methodology in IR and PolSci has become eclipsed by the advent of computational social science as a metabridge between extreme ends of hard sciences and social sciences.
There is no one single gateway to computational social science. It is rather a meeting point between diverse disciplines that seek to strengthen their analytical With the emergence of digital platforms and social media, and global proliferation of smartphones, ComSoc departed from its previous focus and began harvesting this new, abundant and highly granular type of digital data. Current definitions of ComSoc therefore distinguish between computer-based social science 16 , which is using computer programs to process quantitative social data and ComSoc, which processes enormous chunks of -often real-time -Internet data 17 . Although the quantity and granularity of digital data produced every day is impressive, a key question remains how to process such data in a meaningful way and how to build social theory using it. As of July 2016, Instagram, Twitter, Facebook and other social media platforms combined, produced around 650 million publicly available posts per day 18 , making up ’the largest increase in the expressive capacity of humanity in the history of the world’ 19 . With the emergence of increasingly more powerful computers, along with most creative data processing software, all scientific disciplines gained access to historically unprecedented and unfathomably detailed information on micro and macro-level human interactions.
Computational IR (hereafter, ComInt) derives largely from the founding and advent of ComSoc. in the last few years. Related to, but separate from ComSoc, ComInt deals exclusively with core IR topics of power, conflict/peace, state behavior, international norms/institutions and the world system/order. As ComInt starts dealing with non-state actors (NGOs, MNCs, media, religious groups, Diasporas, militants etc.) it steers further into the domain of sociology and shares common ground with digital, or tech sociologists. This domain requires even further novel methods, as tracing the transient shifts and trends of non-state actors require a way to bring ethnography close to the field of computational methods that both include, but also expand upon the existing approaches of digital and/or Internet ethnography.
Both data scientists and natural sciences scholars I got the luck of working with at Oxford Internet Institute, Oxford Computer Science Department and the Alan Turing Institute had a distinct interest in the realist strand of IR. They had an automatic tendency to accept states as singular and primary units of analysis in their approaches and without exception, all of them wanted to address questions related to survival, conflict and security -all from a state-centric point of view. Defense, balance of power, armed conflict and resource-infrastructure (capability) oriented research agendas have attracted significantly more computational research attention than other promising approaches in IR such as constructivism, poststructuralism, critical or post-modern theories. This is a shame, as I will demonstrate later on, data mining, entity recognition or geo-statistical mapping methods can successfully challenge a number of these approaches.
Defined in simple terms ComInt, relies on the mining and processing of vast quantities of digital social footprint to study, model and explain world events. In doing that, it transcends the traditional schism between qualitative and quantitative methodology and presents a ’third way’ methodology that frees the researcher from the restrictions of both methodological schools. ComInt predominantly (but not exclusively) uses large chunks of digital footprint and focuses on social online activities that generate enormous quantities of social data. This is one of the reasons why ComInt or ComSoc didn’t exist a decade ago, and also a reason why merely u
…(Full text truncated)…
📸 Image Gallery
Reference
This content is AI-processed based on ArXiv data.
