INTELLIGENT ASSIGNMENT PLAGIARISM DETECTION SYSTEM USING MACHINE LEARNING

In summary, the developed system is efficient in identifying similarity between two documents and checking whether any document contains AI-generated content. This is achieved using NLP and machine learning methods such as cosine similarity, TF-IDF vectorization, and AI detection. The system not only identifies similarity between documents but also classifies the degree of plagiarism in each category, hence offering a detailed output to help users understand the extent of plagiarism. Integration of different components such as user authentication, document uploading, and results visualization has improved the performance and usability of the system. In addition, the ability to generate reports in various formats makes the system highly useful in both academic and professional settings. The inclusion of AI content detection in the system makes it more relevant in today's era since the number of texts created using machines is increasing day by day. The project has effectively applied NLP and machine learning techniques in solving the problem.

[1]   J. Ramos, “Using TF-IDF to Determine Word Relevance in Document Queries,” in Proc. 1st Instructional Conf. Machine Learning, 2003, pp. 133–142. [2]   G. Salton and C. Buckley, “Term-weighting approaches in automatic text retrieval,” Inf. Process. Manage., vol. 24, no. 5, pp. 513–523, 1988.  [3]       T. Mikolov et al., “Efficient Estimation of Word Representations in Vector Space,” in Proc. ICLR, 2013. [4]   J. Pennington, R. Socher, and C. Manning, “GloVe: Global Vectors for Word Representation,” in Proc. EMNLP, 2014, pp. 1532–1543. [5]    T. Kenter and M. de Rijke, “Short Text Similarity with Word Embeddings,” in Proc. CIKM, 2015, pp. 1411–1420. [6]    A. Radford et al., “Language Models are Unsupervised Multitask Learners,” OpenAI Technical Report, 2019. [7]   J. Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL, 2019, pp. 4171–4186. [8]    Y. Liu et al., “RoBERTa: A Robustly Optimized BERT Pretraining Approach,” 2019. [9]  T. Brown et al., “Language Models are Few-Shot Learners,” in Proc. NeurIPS, 2020. [10]     S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python, O’Reilly, 2009.