Sociology, Department of
Date of this Version
2-26-2019
Document Type
Article
Citation
Presented at “Interviewers and Their Effects from a Total Survey Error Perspective Workshop,” University of Nebraska-Lincoln, February 26-28, 2019.
Abstract
One common trend in the world of survey data collection is the increasing use of new technological developments which can change the nature of the survey interview. A fairly recent trend is the use of machine-learning techniques to customize questions for respondents. This has the potential to create an individualized experience for the respondent and to improve data quality. Nevertheless, little is known so far of how customization affects the interaction in the survey interview.
We introduce a tool developed by Schierholz et al. (2018) to code respondents’ occupation categories during the survey. The tool uses supervised learning algorithms to predict occupation categories based on previously entered text. We use this example to discuss theoretical and practical implications of customization for the interaction between the interviewer and the respondent.
Preliminary results based on behavior coding of interviews will be presented that show that customization based on machine learning may lead to challenges in the standardized survey interview, particularly for the interviewer.
For future research, we propose an experimental study to investigate differences between conversational and standardized interviewing techniques when working with customized survey instruments. In particular, we will focus on whether interviewers are able to exclude obviously inadequate response options and how this effects interview duration as well as perceived burden on the respondent and the interviewer.
Comments
Copyright 2019 by the authors.