Discriminant Validity: Disentangling Health and Emotional Constructs from Language-Based Assessments
Feltman, S., Ganesan, A. V., Ringwald, W., Schwartz, H. A., Kotov, R., Luft, B., Boyd, R., & Kjell, O. (2026). Discriminant Validity: Disentangling Health and Emotional Constructs from Language-Based Assessments. Proceedings of the 11th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026), 43–55. https://doi.org/10.18653/v1/2026.clpsych-1.4
@inproceedings{feltman2026discriminant,
title = {{Discriminant Validity: Disentangling Health and Emotional Constructs from Language-Based Assessments}},
author = {Scott Feltman and Adithya V. Ganesan and Whitney Ringwald and H. Andrew Schwartz and Roman Kotov and Benjamin Luft and Ryan Boyd and Oscar Kjell},
year = {2026},
booktitle = {CLPsych 2026},
doi = {10.18653/v1/2026.clpsych-1.4},
url = {https://doi.org/10.18653/v1/2026.clpsych-1.4}
}
Abstract
Language-based assessments have demonstrated high convergent validity with corresponding mental and physical health constructs, however often fail to address discriminant validity - the measure's ability to distinguish the target construct from related ones. This is a common phenomenon within the domain of mental health, as well as comorbidity with physical health conditions. Identifying key features of individual dimensions of mental and physical health present in language can unlock new avenues of research for natural language processing and psychology. We propose two augmentations to the objective function of the Ridge model, deriving closed-form solutions compatible with Singular Value Decomposition-based solvers, to enforce discriminant validity of off-target constructs using Mean Squared Error (MSE) and Squared Cosine Similarity (SCS,) both having widespread use in contrastive learning. By varying the discrimination strength, we find that a decrease in 0.005 Pearson correlation points can result in a Pearson correlation point increase upwards of 0.132 in discriminant validity for mental and physical health constructs derived from self-reported questionnaires. We see similar improvements across multiple fundamental psychopathology dimensions simultaneously, increasing discriminant validity by 0.012 with stronger increases coming from more noisy, less reliable constructs. Our contributions provide a theoretically grounded path towards improving confidence in language-based assessments in the clinical sector, improving specificity of said assessments to various areas of health.
