Sentiment Analysis Project

Overview

This project focuses on sentiment analysis, applying Machine Learning and Natural Language Processing (NLP) techniques to classify text sentiment as positive, negative, or neutral.

Features

• Preprocessing pipeline: Tokenization, stopword removal, and lemmatization
• Modeling: Implemented using classifiers like Naïve Bayes, SVM, and LSTMs
• Evaluation Metrics: Accuracy, F1-score, and confusion matrices
• Dataset: Utilizes labeled datasets for supervised learning

Repository

🔗 GitHub Repo: Sentiment Analysis

Installation & Usage

Clone the repository and install dependencies:

git clone https://github.com/joaovasco01/SentimentAnalysis.git
cd SentimentAnalysis
pip install -r requirements.txt

Run the model:

python train.py

Example

Below is a sample output from the model predicting the sentiment of a review:

Input: "The product is amazing and works flawlessly!"
Predicted Sentiment: Positive  

Future Improvements

• Fine-tuning models with larger datasets
• Enhancing explainability with SHAP/LIME
• Expanding to multi-language sentiment analysis

This portfolio entry showcases an advanced Sentiment Analysis implementation, leveraging AI and NLP for text classification. 🚀