Learning to Pay Attention: Unsupervised Modeling of Attentive and Inattentive Respondents in Survey Data

Researchers developed an unsupervised machine learning framework using autoencoders and probabilistic models to detect inattentive survey respondents without traditional attention checks. The study found that survey structure is more important than model complexity for detection effectiveness, with well-designed instruments enabling reliable identification of low-quality responses.

• →A new label-free framework combines geometric reconstruction and probabilistic dependency modeling to detect inattentive survey respondents.
• →Survey structure matters more than AI model complexity for effective detection of poor-quality responses.
• →Surveys with coherent, overlapping item batteries create strong covariance patterns that improve algorithmic detection.
• →The framework reveals 'Psychometric-ML Alignment' where good survey design principles also maximize AI detectability.
• →The approach provides a scalable, domain-agnostic tool for survey platforms to audit data quality without additional respondent burden.