Chapter 5.2: Assessing the Relationship between Machine Learning and Open Source Research in International Security

The growth of information technologies, digital data and the internet has led to a vast increase in open source data. The scale of expansion is such that it can be difficult, or even impossible, for open source researchers to access and process all relevant data manually. Accordingly, many are looking to automated tools to help with these tasks. One such tool is machine learning – the use of algorithms that ‘learn’ how to categorize and classify data. This approach has huge potential, but it is also not necessarily straightforward to deploy effectively. This chapter explains core components of machine learning, and how it can be usefully integrated within open source research.