Online Program Home
My Program

Abstract Details

Activity Number: 295 - SPEED: Big Data, Small Area Estimation, and Methodological Innovations Under Development, Part 1
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
Sponsor: Survey Research Methods Section
Abstract #301864
Title: Why Machines Matter for Survey and Social Science Researchers: Exploring How Machine Learning Methods Can Be Applied to the Design, Collection and Analysis of Social Science Data
Author(s): Antje Kirchner* and Trent Burskirk
Companies: RTI International and Bowling Green State University
Keywords: machine learning; survey research process; meta-analysis
Abstract:

The exponential growth of computing power and cheap data storage have nourished artificial intelligence applications and machine learning methods advancing research in medicine, marketing, and many other fields. Despite the rising popularity, the potential of machine learning in survey and social science research has not yet been fully explored. This paper provides an overview of how data science methods have been and can be applied to the social sciences from the perspective of the survey research process including: questionnaire design and evaluation; sampling; tailored survey designs and data collection; weighting adjustment and analysis. We illustrate how these methods can be used to augment, support, reimagine, improve and in some places replace the current methodologies. While machine learning is likely not to replace all human aspects of the survey research process, these methods can offer new ways to approach traditional problems and can provide more efficiency, reduced errors, improved measurement and more cost effective processing. We also discuss how errors in the machine learning process can impact errors we traditionally manage within the survey research process.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program