StressDetection / README.md
EnYa32's picture
Update README.md
7b2487f verified
|
Raw History Blame Contribute Delete
1.2 kB
metadata
title: StressDetection
emoji: 🧘
colorFrom: red
colorTo: red
sdk: docker
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: NLP app to detect stress in social media posts.
license: mit

🧠 Stress Detection from Text

This project is a simple NLP application that detects stress in social media text.

The app uses a TF-IDF Vectorizer and Logistic Regression to classify text as Stress (1) or No Stress (0).


πŸš€ Demo

Users can enter a text (for example a social media post), and the model will predict whether the text shows signs of stress.


🧠 Model Overview

  • Text Preprocessing: TF-IDF Vectorization
  • Model: Logistic Regression
  • Task: Binary Text Classification
  • Labels:
    • 0 β†’ No Stress
    • 1 β†’ Stress

The model achieved an accuracy of about 74% on the test set.


πŸ“‚ Files in This Repository

  • streamlit_app.py β†’ Streamlit application
  • tfidf_lr_pipeline.pkl β†’ Trained TF-IDF + Logistic Regression pipeline
  • requirements.txt β†’ Required Python libraries

▢️ How to Run Locally

pip install -r requirements.txt
streamlit run streamlit_app.py