Active Matrix Factorization for Surveys
Chelsea Zhang, Sean J. Taylor, Curtiss Cobb, and Jasjeet Sekhon

TL;DR
This paper introduces an active matrix factorization approach to reduce survey length by intelligently selecting questions, improving imputation accuracy and survey efficiency through a probabilistic, data-driven method.
Contribution
It presents a novel active question selection method using matrix factorization, enabling automated, efficient survey design with fewer questions and improved response imputation.
Findings
Active question selection improves imputation accuracy.
Efficiency gains over baseline sampling methods.
Heterogeneous reduction in imputation error across questions.
Abstract
Amid historically low response rates, survey researchers seek ways to reduce respondent burden while measuring desired concepts with precision. We propose to ask fewer questions of respondents and impute missing responses via probabilistic matrix factorization. A variance-minimizing active learning criterion chooses the most informative questions per respondent. In simulations of our matrix sampling procedure on real-world surveys, as well as a Facebook survey experiment, we find active question selection achieves efficiency gains over baselines. The reduction in imputation error is heterogeneous across questions, and depends on the latent concepts they capture. The imputation procedure can benefit from incorporating respondent side information, modeling responses as ordered logit rather than Gaussian, and accounting for order effects. With our method, survey researchers obtain…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMobile Crowdsensing and Crowdsourcing · Machine Learning and Algorithms · Expert finding and Q&A systems
