Beyond classification metrics: a psychometric-aware benchmark for data augmentation in imbalanced student mental health surveys.

Background: Machine-learning-based depression screening from student survey data complements clinician assessment but faces two obstacles: class imbalance (causing under-prediction of urgent minority cases) and the untested assumption that synthetic augmentation data preserve psychometric validity. Although recent work has begun to evaluate distributional fidelity of synthetic survey data, no study has systematically benchmarked both classification utility and classical construct-validity measures on augmented student-mental-health datasets. Objective: Benchmark eight data-augmentation strategies on their classification utility and construct validity using a dual-axis evaluation framework. Methods: We evaluated no augmentation, random oversampling, SMOTE, BorderlineSMOTE, ADASYN, CTGAN, TVAE, and the proposed Psychometric-Constrained Tabular GAN (PCT-GAN) on three public datasets (PHQ-9: Results: Overall, the eight methods were not statistically distinguishable on Macro-F1 (Friedman Conclusions: Embedding construct-validity constraints into generative models produces synthetic mental-health data that is simultaneously useful for prediction and trustworthy for secondary research reuse. Practitioners should select SMOTE-family oversamplers for transient training-set augmentation, and PCT-GAN when synthetic data will be shared, re-analysed, or pooled with real samples for downstream psychometric research.