Plagarism Checker

[WannaCry016]

Problem

-Identifying similarities between text files is essential in academic and professional environments to detect potential plagiarism. Manually checking for overlapping content can be time-consuming and inefficient.

Solution

-Developed a Python script using scikit-learn to automate plagiarism detection. The script reads .txt files in the directory, converts their content into numerical vectors using TF-IDF, and calculates cosine similarity scores between them to determine the extent of similarity.

Changes proposed in this Pull Request :

• Added plag.py, which uses TfidfVectorizer to vectorize text documents and cosine_similarity to measure similarity between pairs of files.
• Implemented a function to loop through each document, comparing it with others in the directory and calculating similarity scores.
• Stored results in a set plagiarism_results, displaying file pairs with their respective similarity scores.
• Ensured compatibility with .txt files and UTF-8 encoding for broader accessibility across text sources.