BERT-Enhanced Retrieval Tool for Homework Plagiarism Detection System

TL;DR

This paper introduces a BERT-enhanced retrieval system for homework plagiarism detection, utilizing GPT-3.5 generated datasets and achieving high accuracy, precision, recall, and F1 scores in identifying plagiarized texts.

Contribution

It presents a novel dataset generation method using GPT-3.5 and a high-efficiency plagiarism detection approach based on BERT and Faiss, improving detection performance.

Findings

Achieved over 98.8% accuracy and F1 score in plagiarism detection.

Generated 32,927 diverse plagiarism detection datasets with GPT-3.5.

Developed a user-friendly demo platform for plagiarism analysis.

Abstract

Text plagiarism detection task is a common natural language processing task that aims to detect whether a given text contains plagiarism or copying from other texts. In existing research, detection of high level plagiarism is still a challenge due to the lack of high quality datasets. In this paper, we propose a plagiarized text data generation method based on GPT-3.5, which produces 32,927 pairs of text plagiarism detection datasets covering a wide range of plagiarism methods, bridging the gap in this part of research. Meanwhile, we propose a plagiarism identification method based on Faiss with BERT with high efficiency and high accuracy. Our experiments show that the performance of this model outperforms other models in several metrics, including 98.86\%, 98.90%, 98.86%, and 0.9888 for Accuracy, Precision, Recall, and F1 Score, respectively. At the end, we also provide a user-friendly demo platform that allows users to upload a text library and intuitively participate in the plagiarism analysis.