Comment2Score

Overview

Comment2Score, is an exploratory and analytical project focused on sentiment analysis derived from the Rate My Professors (RMP) website. The project aims to uncover insights into professor ratings, difficulty levels, and the overall sentiment from student reviews using various data science and machine learning techniques.

Key Features

• Data Visualization: Utilizes kernel density estimate plots, count plots, and various graphical representations to analyze star ratings, difficulty levels, and grade distributions from the dataset.
• Approach 1 - Topic Modeling: Employs topic modeling techniques to identify key themes in student reviews and evaluates model performance with accuracy metrics on star ratings and difficulty levels.
• Approach 2 - Sentiment Intensity Analysis, Version 1: Implements Sentiment Intensity Analysis to quantify the sentiment of reviews, followed by a detailed exploration of preprocessing steps, model architecture, and predictions.
• Approach 3 - Sentiment Intensity Analysis, Version 2: Offers an alternative or supplementary method for sentiment analysis, including unique preprocessing and analysis steps.
• Miscellaneous: Details about the dataset, its sources, and potential future directions for this research project.

Getting Started

To run this notebook:

1. Ensure you have Jupyter Notebook or JupyterLab installed. If not, you can install it using pip:

   pip install notebook
   

   or

   pip install jupyterlab
   

2. Clone this repository to your local machine.
3. Navigate to the cloned directory and start Jupyter Notebook or JupyterLab.
4. Open the Comment2Score_Final.ipynb notebook.

Prerequisites

This notebook requires Python 3.x and the following libraries:

• numpy
• pandas
• matplotlib
• seaborn
• scikit-learn
• nltk You can install these packages using pip:

pip install numpy pandas matplotlib seaborn scikit-learn nltk

Contributing

Contributions and suggestions to improve the analysis and expand the scope of this project are welcomed! If you have ideas or want to contribute, please open an issue or submit a pull request.

License

This project is open-sourced under the MIT License. See the LICENSE file for more details.

Acknowledgments

• Thanks to Rate My Professors for the dataset.