XGBoost models trained on Screenome screenshot features and CES-D scores predict within-person depressive symptom change with AUCs of 0.906 and 0.755 under temporal holdout, generalizing to unseen people at AUC 0.821.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Within-person prediction of depressive symptom change using year-long Screenome data and CES-D assessments
XGBoost models trained on Screenome screenshot features and CES-D scores predict within-person depressive symptom change with AUCs of 0.906 and 0.755 under temporal holdout, generalizing to unseen people at AUC 0.821.