Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195789,
        author = {Jella Navya sri and Kuntla Divya and Abhishek Goud and G.sravani},
        title = {Research integrity monitor - verifying the authenticity of academic content},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {830-836},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195789},
        abstract = {In recent years, the rapid evolution of AI-generated content and the development of digital academic resources, ensuring research integrity in scholarly documents has become a challenge. Existing solutions such as Bi-LSTM-based AI text detectors, transformer-based NLP models, and blockchain-based certificate verification systems only focus on a few aspects of research integrity verification. These approaches provide moderate accuracy. This paper presents a Research Integrity Monitor that offers a comprehensive framework for research integrity verification. This framework includes plagiarism detection through NLP-based approaches, AI-generated content detection, multilingual language detection, citation detection, and certificate verification through optical character recognition. The system uses TF-IDF with cosine similarity, machine learning algorithms, and optical character recognition to analyze the academic documents. The model provides a score that reflects the research integrity. The results of the experiment prove that the model achieves 97.8% accuracy, 97.2% precision, 96.9% recall, and a high F1-score of 97% with a low error rate of 2.2%, outperforming existing solutions such as Bi-LSTM-based AI text detectors that provide a high accuracy of only 91-93% and traditional plagiarism detection systems that provide a high accuracy of only 90-97%.},
        keywords = {Research Integrity, AI-Generated Text Detection, Plagiarism Detection, Natural Language Processing, Machine Learning, Certificate Authentication, OCR, Citation Verification.},
        month = {April},
        }