Federated learning matches centralized F1 scores for mental health detection from social media but differentially private federated learning drops up to 27 F1 points even at epsilon=50 because noise distorts sparse health and emotion markers.
Jay Gala, Deep Gandhi, Jash Mehta, and Zeerak Talat
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
Federated learning matches centralized F1 scores for mental health detection from social media but differentially private federated learning drops up to 27 F1 points even at epsilon=50 because noise distorts sparse health and emotion markers.