Loading repository data…
arupdas0825 / repository
A Python-based Sentiment Analysis web app that detects emotions in text using NLP. Built with TextBlob & Streamlit, it supports single text, bulk, and CSV analysis with real-time visualizations. Designed for scalability with upcoming BERT integration, REST API, and multilingual support.
A production-grade NLP-powered Sentiment Analysis platform built with multi-engine support, REST API, multilingual detection, and real-time analytics dashboard.
| Engine | Speed | Accuracy | Best For |
|---|---|---|---|
| VADER | ⚡ Fast | ~85% | Social media, slang |
| TextBlob | ⚡⚡ Very Fast | ~70% | Simple text |
| BERT | 🐢 Slow | ~92% | High accuracy tasks |
| Method | Endpoint | Description |
|---|---|---|
| GET | /health | API status check |
| GET | /engines | Available engines info |
| POST | /analyze | Single text analysis |
| POST | /analyze-bulk | Bulk text (max 100) |
| POST | /analyze-csv | CSV file upload |
📖 Swagger UI: http://127.0.0.1:8000/docs
pytestflake8| Category | Technology |
|---|---|
| Language | Python 3.11 |
| UI | Streamlit |
| NLP | TextBlob, VADER, BERT (DistilBERT) |
| API | FastAPI + Uvicorn |
| Translation | Googletrans, Langdetect |
| Data | Pandas |
| Visualization | Matplotlib, WordCloud |
| Testing | Pytest, Flake8 |
| CI/CD | GitHub Actions |
| Deployment | Streamlit Cloud |
sentiment-analysis-project/
│
├── .github/
│ └── workflows/
│ └── ci.yml # GitHub Actions CI/CD
│
├── data/
│ ├── sample.csv # Sample dataset
│ └── imdb.csv # IMDB movie reviews dataset
│
├── tests/
│ └── test_analyzer.py # Unit tests (7 tests)
│
├── app.py # Main Streamlit UI
├── analyzer.py # Multi-engine NLP logic
├── api.py # FastAPI REST API
├── dashboard.py # Analytics dashboard
├── translator.py # Multilingual support
├── utils.py # Helper functions
├── requirements.txt # Dependencies
└── README.md
# Clone the repository
git clone https://github.com/arupdas0825/sentiment-analysis-project.git
cd sentiment-analysis-project
# Create virtual environment
python -m venv venv
venv\Scripts\activate # Windows
source venv/bin/activate # Mac/Linux
# Install dependencies
pip install -r requirements.txt
python -m textblob.download_corpora
streamlit run app.py
uvicorn api:app --reload
# Swagger UI → http://127.0.0.1:8000/docs
pytest tests/ -v
| Text | Engine | Label | Polarity | Confidence |
|---|---|---|---|---|
| I love Python! | VADER | 😊 Positive | 0.677 | 67.7% |
| This is terrible | VADER | 😞 Negative | -0.68 | 68.0% |
| আমি খুশি | VADER+Translate | 😊 Positive | 0.59 | 59.0% |
tests/test_analyzer.py
✅ test_positive_sentiment
✅ test_negative_sentiment
✅ test_empty_text
✅ test_textblob_engine
✅ test_multiple_texts
✅ test_confidence_score
✅ test_result_keys
7 passed in 2.3s
Arup Das
B.Tech CSE (AIML) — Brainware University
🎯 Targeting MSc in Germany
This project is licensed under the MIT License.
Selected from shared topics, language and repository description—not editorial ratings.
0x0be /
A user-friendly python-based GUI which provides sentiment analysis of users' reviews toward a specific TripAdvisor facility
rohanmistry231 /
A collection of Python-based NLP projects exploring text processing, sentiment analysis, and language modeling using libraries like NLTK, SpaCy, and Transformers. Includes hands-on implementations with datasets and tutorials for building and evaluating NLP models.
avikds /
A Python-based sentiment analysis tool that uses Scikit-Learn and a Naive Bayes classifier to predict tweet sentiment with 95% accuracy.
rohanmistry231 /
Description A Python-based web application for analyzing sentiment in movie reviews using NLP techniques and machine learning models. Built with Flask and libraries like NLTK or TextBlob, it provides a user-friendly interface for sentiment classification.
AshirwadSatapathi /
Student Feedback Analyzer is a Python-based desktop application which is developed with a motive to change the existing feedback system used in colleges that uses multiple options in the form of radio button in a form to find out the feedback of the student on a particular subject or a faculty instead use sentiment analysis to find out the feedback score of a subject or faculty from the students feedback. The application uses textblob to find the polarity of a feedback given by the subject and stores it in a database. Later the Administrator can find out the feedback score of each faculty and / or subject using the admin module.
Ashok-777 /
CustomerExpenseChurn-py is a Python-based analytics tool that combines expense analysis, customer feedback sentiment, and machine-learning churn prediction to generate insights, visualizations, and retention recommendations from data.
