Artificial Intelligence-Based Automatic Text Detection System Using Multi-Layer Pattern Recognition 387 528
DOI:
https://doi.org/10.26623/transformatika.v23i2.13256Keywords:
12 Algoritma, Deteksi AI, Pengenalan Pola, Klasifikasi TeksAbstract
The rapid advancement of generative AI models such as ChatGPT, Claude, and Gemini raises serious concerns about the authenticity of academic and professional documents. This study develops a detection system that uses a combination of linguistic, structural, and statistical pattern analysis to identify AI-generated text and classify the responsible AI model. The system analyzes more than 12 different parameters from uploaded documents (PDF, DOCX, TXT formats). The detection engine operates through seven analytical layers: signature detection, linguistic analysis, word pattern analysis, structural analysis, feature pattern analysis, vocabulary and grammar assessment, and AI fingerprinting. The scoring mechanism provides a general AI probability score (0-100%) and individual probability scores for 10 different AI models. In testing with 100 documents, the system achieved 76.8% accuracy in identifying AI-generated text and 87.3% accuracy in classifying the source AI model. Sentence entropy analysis, paragraph uniformity assessment, and distinctive linguistic markers proved most effective. This study demonstrates that multi-layer pattern recognition is a viable approach for detecting and classifying AI-generated text, with implications for academic integrity, content verification, and digital forensics.
Downloads
References
T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child and A. Ramesh, Language Models are Few-Shot Learners, in Advances in Neural Information Processing Systems 33 (NeurIPS 2020), Vancouver, Canada, 2020.
J. Devlin, M.-W. Chang, K. Lee and K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in Proceedings of NAACL-HLT 2019, Minneapolis, Minnesota, 2019.
T. Susnjak and T. R. McIntosh, ChatGPT: The End of Online Exam Integrity?, Education Sciences, vol. 14, no. 6, pp. 1-20, 2024.
W. Liang, M. Yuksekgonul, Y. Mao, E. Wu and J. Zou, GPT detectors are biased against non-native English writers, Patterns, vol. 4, no. 7, pp. 1-4, 2023.
K. Yoo, W. Ahn, Y. Song and N. Kwak, Exploring Causal Mechanisms for Machine Text Detection Methods, in Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), Mexico City, Mexico, 2024.
S. K. Kar, T. Bansal, S. Modi and A. Singh, How Sensitive Are the Free AI-detector Tools in Detecting AI-generated Texts? A Comparison of Popular AI-detector Tools, Indian Journal of Psychological Medicine, vol. 47, no. 3, pp. 275-278, 2024.
S. Wang, F. Wang, Z. Zhu, J. Wang, T. Tran and Z. Du, Artificial intelligence in education: A systematic literature review, Expert Systems with Applications, vol. 252, pp. 1-19, 2025.
I. Solaiman, M. Brundage, J. Clark, A. Askell, A. Herbert-Voss, J. Wu, A. Radford, G. Krueger, J. W. Kim, S. Kreps, M. McCain, A. Newhouse, J. Blazakis, K. McGuffie and J. Wang, Release Strategies and the Social Impacts of Language Models, OpenAI, California, USA, 2019.
H. Suh, M. Tafreshipour, J. Li and I. Ahmed, An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?, in ICSE 25: Proceedings of the IEEE/ACM 47th International Conference on Software Engineering, Ottawa Ontario Canada, 2025.
Z. Yu, X. Li, X. Niu, J. Shi and G. Zhao, Face Anti-Spoofing with Human Material Perception, in Computer Vision – ECCV 2020: 16th European Conference, Glasgow, United Kingdom, 2020.
D. Weber-Wulff, A. Anohina-Naumeca, S. Bjelobaba, T. Foltýnek, J. Guerrero-Dib, O. Popoola, P. Šigut and L. Waddington, Detecting AI-Generated Text in Educational Content: Leveraging Machine Learning, International Journal for Educational Integrity, vol. 19, no. 26, pp. 1-39, 2023.
V. S. Sadasivan, A. Kumar, S. Balasubramanian, W. Wang and S. Feizi, Can AI-Generated Text be Reliably Detected?, in The Twelfth International Conference on Learning Representations - ICLR 2024, Vienna Austria, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Kartika Imam Santoso, Edi Widodo, Theresia Widji Astuti
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Transformatika is licensed under a Creative Commons Attribution 4.0 International License.
