PLAGIARISM DETECTION USING DEEP LEARNING

Abstract

PLAGIARISM DETECTION USING DEEP LEARNING, is a detection System for detecting plagiarism using deep learning techniques. Plagiarism is the act of using or presenting someone else’s work, ideas, or words as your own without giving proper credit or acknowledgment to the source. It is considered a serious academic and ethical offense in most settings, including academia, journalism, and creative industries. The procedure of human-based plagiarism detection is time-consuming, inaccurate, and difficult. The proposed system for plagiarism detection using deep learning aims to detect instances of plagiarism and identify paraphrased content.This Project proposes a plagiarism detection System based on two deep learning models: A combination of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), and a Transformer-based model. This project compares the effectiveness of a transformer-based model, and the combination of the CNN-LSTM model and also identifies various types of plagiarism including paraphrasing. In terms of outcomes, research has demonstrated that deep learning models can accurately identify plagiarism. One model is the combination of the CNN-LSTM model to detect plagiarism and had a 99.51% success rate. Another model such as a transformer-based model detects plagiarism with a high accuracy rate such as 99.61%