Feedback Clustering Using Sentence Transformers

Overview

This project aims to cluster feedback texts using advanced natural language processing techniques. It utilizes Sentence Transformers for generating meaningful embeddings of feedback sentences, followed by KMeans clustering to group similar feedback together.

Features

• Sentence Embeddings: Utilizes state-of-the-art Sentence Transformers to convert feedback texts into numerical representations.
• Unsupervised Clustering: Applies KMeans clustering to organize feedback into distinct groups based on similarity.
• Visualization: Includes visual tools such as the Elbow Method and Silhouette Score to determine optimal cluster numbers.

Getting Started

Installation

1. Clone the repository:
2. Install dependencies:

Usage

1. Prepare your feedback data in a CSV format (data.csv).
2. Run notebook.ipynb to generate clusters and visualize results:
3. View the output clusters and explore insights from the feedback data.

Requirements

• Python 3.6+
• Dependencies listed in requirements.txt

Contributing

Contributions are welcome! Please fork the repository and submit pull requests for new features, improvements, or bug fixes.