https://github.com/atchayaah/customer-feedback-emotion-analyzer
AI-based web app that detects emotions from text using NLP and ML. Developed as part of the IBM Gen AI course on Coursera.
https://github.com/atchayaah/customer-feedback-emotion-analyzer
coursera-project emotion-detection flask machine-learning nlp python
Last synced: 2 months ago
JSON representation
AI-based web app that detects emotions from text using NLP and ML. Developed as part of the IBM Gen AI course on Coursera.
- Host: GitHub
- URL: https://github.com/atchayaah/customer-feedback-emotion-analyzer
- Owner: atchayaah
- Created: 2025-08-31T07:39:21.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-09-13T07:58:57.000Z (10 months ago)
- Last Synced: 2025-09-13T10:01:18.776Z (10 months ago)
- Topics: coursera-project, emotion-detection, flask, machine-learning, nlp, python
- Language: Python
- Homepage:
- Size: 352 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Customer Feedback Emotion Analyser
An AI-powered web application that analyzes customer feedback and detects the underlying emotions. This project leverages Natural Language Processing (NLP) and Machine Learning techniques to classify emotions from text input, helping businesses better understand customer sentiment.
## 📝Features
🔹 Detects emotions such as Happy, Sad, Angry, Neutral, Fear, Surprise, Disgust
🔹 User-friendly web interface for real-time emotion detection
🔹 Built with Machine Learning & NLP techniques
🔹 Scalable for integration into e-commerce platforms, chatbots, and feedback systems
## 📝Tech Stack
**Frontend**: HTML
**Backend**: Python (Flask / Streamlit)
**Libraries & Tools**:
pandas, numpy – Data preprocessing
scikit-learn – ML models
nltk / spacy – NLP processing
Flask / Streamlit – Web app deployment
## 📝Deployment
To deploy this project run
1️⃣ Clone the repository
git clone https://github.com/atchayaah/customer-feedback-emotion-analyser.git
cd customer-feedback-emotion-analyser
2️⃣ Create a virtual environment
python -m venv venv
source venv/bin/activate # On Mac/Linux
venv\Scripts\activate # On Windows
3️⃣ Install dependencies
pip install -r requirements.txt
4️⃣ Run the application -
python app.py
The app will be available at:
👉 http://127.0.0.1:5000/
## 📝 Model training & Use Case
• Preprocess data (handle missing values, encode categorical variables, scale features)
• Train machine learning models (Naive Bayes, Logistic Regression, or Neural Networks).
• Save the trained model using Pickle/Joblib for deployment.
**Use Cases**
📌 E-commerce feedback analysis – Detect customer satisfaction trends.
📌 Social media monitoring – Track public emotions on brands/events.
📌 Chatbots & virtual assistants – Enhance emotional intelligence.
## 📜License
The project was developed as part of the **IBM GEN AI ENGINEERING on Coursera**.