Update README.md

README.md

@@ -10,10 +10,81 @@ tags:
 pinned: false
 short_description: Streamlit template space
 ---
+# 🎬 IMDb Movie Review Sentiment Analysis
 
-# Welcome to Streamlit!
+This app predicts whether a movie review is **positive** or **negative** using a Machine Learning model trained on the IMDb dataset.
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+🔗 **Live App:** (add your Hugging Face link here)
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+---
+
+## 📌 Project Overview
+
+Sentiment analysis is a Natural Language Processing (NLP) task that determines the emotional tone behind a piece of text.
+
+In this project:
+
+- User enters a movie review
+- The text is transformed using **Bag-of-Words (CountVectorizer)**
+- A **Logistic Regression** model predicts the sentiment
+
+---
+
+## 🧠 Model Details
+
+- **Algorithm:** Logistic Regression  
+- **Vectorizer:** CountVectorizer (max_features = 5000, English stopwords removed)  
+- **Train/Test Split:** 80 / 20  
+- **Evaluation Metric:** Accuracy  
+
+✅ **Accuracy:** ~0.87  
+
+The dataset is balanced between positive and negative reviews, making accuracy a reliable metric.
+
+---
+
+## 📂 Dataset
+
+IMDb Dataset of 50K Movie Reviews  
+Each review is labeled as:
+
+- `positive`
+- `negative`
+
+---
+
+## ⚙️ How It Works
+
+1. User enters a movie review in the app
+2. The review is converted into numerical features using the trained vectorizer
+3. The model predicts the sentiment
+4. The app displays:
+   - Predicted class
+   - Confidence score
+
+---
+
+## 🖥️ App Features
+
+✔ Real-time sentiment prediction  
+✔ Confidence probability  
+✔ Clean and interactive UI  
+✔ Handles raw text input  
+
+---
+
+## 🛠️ Tech Stack
+
+- Python
+- Scikit-learn
+- Pandas
+- Streamlit
+- Joblib
+
+---
+
+## 🚀 Run Locally
+
+```bash
+pip install -r requirements.txt
+streamlit run streamlit_app.py