Machine Learning for Social Science: An Agnostic Approach

Abstract

Social scientists are now in an era of data abundance, and machine learning tools are increasingly used to extract meaning from data sets both massive and small. We explain how the inclusion of machine learning in the social sciences requires us to rethink not only applications of machine learning methods but also best practices in the social sciences. In contrast to the traditional tasks for machine learning in computer science and statistics, when machine learning is applied to social scientific data, it is used to discover new concepts, measure the prevalence of those concepts, assess causal effects, and make predictions. The abundance of data and resources facilitates the move away from a deductive social science to a more sequential, interactive, and ultimately inductive approach to inference. We explain how an agnostic approach to machine learning methods focused on the social science tasks facilitates progress across a wide range of questions. Expected final online publication date for the Annual Review of Political Science, Volume 24 is May 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

A Mixed Methods Study of Public Perception of Social Distancing: Integrating Qualitative and Computational Analyses for Text Data

“…Our findings suggest that structural topic modeling is a comparable approach to an exploratory, descriptive qualitative analysis. There are a variety of computational text analysis methods besides the structural topic model that we used in this study, and readers can refer to Grimmer and Stewart (2013)’s article for a more detailed discussion of the different methods and their application for discovery, measurement, and inference in social science (Grimmer et al, 2021). We also want to call attention to a growing body of work that discusses how to integrate computational methods with qualitative methods across disciplines, such as informational science (Baumer et al, 2017), policy studies (Isoaho et al, 2021), and communication research (Ophir et al, 2020).…”

On the conditions for integrating deep learning into the study of visual politics

“…One frequently expressed reason for this is the increased accessibility of computing power, which is needed to learn the typically large number of model parameters. A less celebrated reason (probably because it is common to most areas in machine learning and thus taken for granted) has been identified in the ready availability of benchmark data [18], such as, in the visual context, the ImageNet collection. Using a few common training and test datasets, it has been possible for a very large number of researchers to compute performances and compare them with other proposals, establishing an evolutionary process where the most fit network models survive.…”

Battling COVID-19 using machine learning: A review

“…Referring to available literatures, the applicability of ML and hybridized models successfully in various field of engineering and natural disasters (Abbaszadeh Shahri, Asheghi et al, 2021;Abbaszadeh Shahri, Kheiri et al, 2021;Abbaszadeh Shahri & Maghsoudi Moud, 2020, psychometric analysis (Orrù et al, 2020;Rosenbusch et al, 2021), medical and pharmaceutics (Kan, 2017;Réda et al, 2020;Vamathevan et al, 2019), incorporating with graph theory (Abderrahim et al, 2014) as well as social sciences (N. C. Chen et al, 2018;Grimmer et al, 2021;Hindman, 2015) have been approved.…”