This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognizing you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
How can cutting-edge technology transform the way surveys are conducted? In 2023, Westat experts co-authored a Survey Practice paper, Can Machine Learning Efficiently Evaluate Interviewer Performance?, which demonstrated and discussed how combining Computer-Assisted Recorded Interviewing (CARI) with Machine Learning (ML) improved the efficiency and effectiveness of interviewer monitoring by automatically reviewing recorded interviews in real time
Now, in a follow-up study that has a newly published finding, “Applying Machine Learning to Survey Question Assessment,” researchers highlight how this technology can process a large number of recordings automatically to identify potentially problematic survey questions. Hanyu Sun, PhD, a Westat Principal Statistical Associate, was among the co-authors of this study.
The study validated that the enhanced system successfully identified poor-performing survey questions, matching expert assessments. By combining CARI and ML technology, researchers can efficiently screen and select which questions need conventional behavior coding review. This advancement streamlines the question evaluation process, making CARI more effective for survey development.
This Audio Pipeline which has been developed and maintained by the Survey Methods Group of the Statistics and Data Science Center has been implemented in multiple large-scale data collection to facility quality control, such as the Population Assessment of Tobacco and Health (PATH) study, Medical Expenditure Panel Survey (MEPS), and National Health and Aging Trends Study (NHATS).