Document Plagiarism Detection

Overview

This Python script analyzes Jupyter Notebooks (.ipynb files) to compute similarity between text, code, and cell IDs across multiple notebooks. It performs the following key tasks:

1. Parse Jupyter Notebooks: Extracts text and code cells from notebooks.
2. Calculate Similarities: Uses TF-IDF and cosine similarity to compare text and code, and Jaccard similarity for cell IDs.
3. Identify Unique Cells: Finds cells that are not common across the notebooks and computes their similarities.
4. Combine Similarity Matrices: Combines normalized similarity matrices for text, code, and IDs into a single matrix.

Installation

To install the program:

1. Clone project folder.

git clone https://github.com/JohannFaust666/Document-Plagiarism-Detection.git

2. Create virtual env:

python3 -m venv venv
source venv/bin/activate

3. Install requirements:

pip install -r requirements.txt

4. Run:

streamlit run app.py

Key Features

1. TF-IDF & Cosine Similarity: Measures the similarity between text and code.
2. Jaccard Similarity: Measures similarity between cell IDs.
3. Matrix Normalization: Ensures each similarity matrix is normalized between 0 and 1.
4. Combines Results: Generates a combined similarity matrix to provide a holistic comparison across notebooks.