Machine learning to detect invalid text responses: Validation and comparison to existing detection methods
Published in Behavior Research Methods, 2022
Recommended citation: Yeung, R. C., & Fernandes, M. A. (2022). Machine learning to detect invalid text responses: Validation and comparison to existing detection methods. Behavior Research Methods, 1–16. https://doi.org/10.3758/s13428-022-01801-y
We propose and implement a supervised machine learning approach that can mimic the accuracy of human coding, but without the need to hand-code entire text datasets. Using autobiographical memory texts, we accurately detected invalid texts with performance near human coding, significantly outperforming existing data quality indicators.
Recommended citation: Yeung, R. C., & Fernandes, M. A. (2022). Machine learning to detect invalid text responses: Validation and comparison to existing detection methods. Behavior Research Methods, 1–16. https://doi.org/10.3758/s13428-022-01801-y