CoolFace
Modelpublic

santa47/cbt-distortion-classifier-v1

sourceHugging Facemitupdated 8mo agoView on Hugging Face
0likes12downloads
Model Card

CBT Cognitive Distortion Classifier

Classifies text into cognitive distortion groups for CBT therapy applications.

Model Details

  • —Best Model: SVM
  • —Model Type: Traditional ML
  • —Classes: 5 distortion groups

Performance

MetricClean DataReal-World
Accuracy0.41880.3781
F1 Score0.41810.3637

Distortion Groups

GroupDistortionsTreatment
G0No DistortionSupportive listening
G1All-or-nothing, LabelingGradient restructuring
G2Overgeneralization, Mind Reading, Fortune-tellingEvidence testing
G3Mental filter, MagnificationAttention rebalancing
G4Emotional Reasoning, Personalization, Should statementsMetacognitive distancing

All Models Compared (Real-World F1)

ModelAccuracyF1 Score
SVM0.37810.3637
Logistic Regression0.34060.3256
Random Forest0.30310.2765
XGBoost0.26560.2538
TinyBERT0.25000.1982

Usage

See config.json for model type and loading instructions.

Disclaimer

For educational and supportive purposes only. Not a substitute for professional mental health care.