Abstract
Artificial Neural Networks (ANNs) are being increasingly used in various disciplines outside computer science, such as bibliometrics, linguistics, and medicine. However, their uptake in the social science community has been relatively slow, because these highly non-linear models are difficult to interpret and cannot be used for hypothesis testing. Despite the existing limitations, this paper argues that the social science community can benefit from using ANNs in a number of ways, especially by outsourcing laborious data coding and pre-processing tasks to machines in the early stages of analysis. Using ANNs would enable small teams of researchers to process larger quantities of data and undertake more ambitious projects. In fact, the complexity of the pre-processing tasks that ANNs are able to perform mean that researchers could obtain rich and complex data typically associated with qualitative research at a large scale, allowing to combine the best from both qualitative and quantitative approaches.
Highlights
It is customary to teach undergraduate social science students the distinctions between “qualitative” and “quantitative” approaches in the very first social science methodology classes
We provide in this paper an overview of one family of algorithms called artificial neural networks (ANNs), which have recently become widely used in business and research spheres due to their capacity to identify and “learn” highly complex and nonlinear data patterns
We present the case why Artificial Neural Networks (ANNs) constitute a significant improvement over the previous generation of algorithms and discuss their features that are of particular interest to social scientists
Summary
It is customary to teach undergraduate social science students the distinctions between “qualitative” and “quantitative” approaches in the very first social science methodology classes. You have qualitative methods, which produce deep and rich insights about a small number of cases but do not allow generalizations.. You have qualitative methods, which produce deep and rich insights about a small number of cases but do not allow generalizations.2 The distinction between these two approaches results from a simple truth: a typical research team does not have the capacity to collect and process enough data to produce rich and detailed insights for the number of cases sufficiently large to be generalizable. Research teams have to make the choice to either produce shallower insights for a large number of cases (quantitative approach) or rich insights for a small number of cases (qualitative approach)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
