VADER Text Sentiment Analyzer

🔎 Sentiment analysis from web pages or text using VADER + Portuguese lexical adaptation

---

📌 Overview

This project performs sentiment analysis on textual content extracted from web pages or raw text. The system accepts a URL or text input, retrieves the content, processes it, and returns a sentiment classification.

It combines:

• Original VADER rule-based sentiment engine (optimized for social media text)
• Portuguese lexical adaptation for improved analysis in PT-BR
• Web scraping module for content extraction

---

⚙️ Features

• Analyze sentiment from a URL
• Analyze pasted text
• Portuguese + English support
• Rule-based NLP (fast + explainable)
• Modular architecture
• Ready for integration into pipelines or APIs

---

🧠 How it Works

1. Receives a URL or text
2. Extracts textual content
3. Normalizes text
4. Applies lexicon rules
5. Computes sentiment score
6. Returns classification

Output example:

Sentiment: Positive
Score: 0.78

---

🧱 Project Structure

project/
│
├── projeto.py            → main execution script
├── data_access.py        → web content extraction
├── text_paste.py         → manual text input
├── center.py             → processing core
├── credit.py             → credits module
├── lexicons/             → sentiment lexicons
├── requirements.txt
└── README.md

---

🚀 Installation

git clone https://github.com/eduardo-data/VADER_text_sentiment
cd VADER_text_sentiment
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install -r requirements.txt

---

▶️ Usage

Analyze a webpage

python projeto.py --url "https://example.com/article"

Analyze text

python projeto.py --text "This news is amazing!"

---

📊 Methodology

This project uses a lexicon + rule-based approach, not machine learning.

Advantages:

• deterministic
• explainable scores
• fast execution
• no training required

---

📚 Credits & References

English Model

Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Proceedings of the 8th International AAAI Conference on Weblogs and Social Media (ICWSM-14).

---

Portuguese Adaptation

Almeida, Rafael J. A. (2018). LeIA — Léxico para Inferência Adaptada

---

📜 License

MIT License — free for academic and commercial use.

---

👨‍💻 Author

Luiz Eduardo Data & NLP Projects

Github - https://github.com/eduardo-data

Linkedin - https://www.linkedin.com/in/luizeduardodatascientist/

---

⭐ Contributing

Pull requests are welcome. For major changes, open an issue first to discuss what you would like to change.

---

🔮 Future Improvements

• API version
• Web interface
• Batch analysis
• Topic modeling integration
• Visualization dashboard

---

If this project helped you, consider giving it a ⭐