Sentiment Analysis Project

This repository contains code and resources for performing sentiment analysis on movie and flight reviews. The project demonstrates the use of various natural language processing (NLP) techniques and machine learning models to classify text data.

Project Overview

Movie Reviews Sentiment Analysis

The movie-reviews-sentiment-analysis.ipynb notebook contains code to process and analyze movie reviews. The project aims to classify the reviews into positive or negative sentiment categories using machine learning models.

Flight Reviews Sentiment Analysis

The flight-review-sentiment-analysis.ipynb notebook focuses on analyzing sentiment from flight reviews. The objective is to categorize reviews into positive, negative or neutral sentiments based on the provided text.

Key Features

• Data Preprocessing: Includes tokenization, stop word removal, and vectorization techniques (e.g., CountVectorizer, TfidfVectorizer).
• Model Training: Implementation of various machine learning models, including logistic regression, Naive Bayes, and support vector machines (SVM).
• Evaluation: Includes model evaluation metrics like accuracy, precision, recall, and F1-score.

Usage

1. Clone the repository:

   git clone https://github.com/yourusername/sentiment-analysis.git

2. Install the required dependencies:

   pip install -r requirements.txt

3. Run the Jupyter notebooks:

   • Open movie-reviews-sentiment-analysis.ipynb or flight-review-sentiment-analysis.ipynb in Jupyter Notebook or Jupyter Lab.
   • Execute the cells to preprocess data, train models, and evaluate the results.

References

This project was developed with reference to the Udemy course:

• Python for Machine Learning & Data Science Masterclass by Jose Portilla