indranil143/Mental-Health-Sentiment-Analysis-using-Deep-Learning

A deep learning project using fine-tuned RoBERTa to classify mental health sentiments from text, aiming to provide early insights and support. ⚕️❤️

34
/ 100
Emerging

Fine-tunes RoBERTa with balanced class weights and AdamW optimization to classify text into seven mental health categories (Anxiety, Depression, Suicidal, etc.), achieving 75.33% accuracy over a baseline Logistic Regression model. The pipeline includes comprehensive text preprocessing with contraction expansion, stopword removal, and lemmatization, alongside EDA with n-gram and word cloud analysis across 50,000+ labeled samples from Kaggle.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 16 / 25

How are scores calculated?

Stars

35

Forks

7

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/indranil143/Mental-Health-Sentiment-Analysis-using-Deep-Learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.