Ritabrata04/Hybrid-Approach-To-Depression-Detection

This repository applies Deep Learning techniques for depression detection in text, using LSTM, GRU, BiLSTM, BERT models, and a baseline FFNN. It also includes data visualizations, autoencoder semantics, KMeans clustering, and detailed performance comparisons.

30
/ 100
Emerging

This helps mental health researchers or clinicians analyze text from online discussions or patient notes to identify potential indicators of depression. You input text conversations, and it classifies them as either 'depression' or 'non-depression,' providing a score for how confident it is in that classification. This tool is designed for mental health professionals or researchers working with large volumes of text data.

No commits in the last 6 months.

Use this if you need to automatically screen or categorize large amounts of text data, such as social media posts or clinical notes, for signs of depression.

Not ideal if you need a diagnostic tool for individual patients or if your primary goal is real-time intervention based on immediate text analysis.

mental-health clinical-research social-listening text-analysis psychology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

19

Forks

2

Language

Python

License

MIT

Last pushed

Jul 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ritabrata04/Hybrid-Approach-To-Depression-Detection"

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