Implementasi GPT API pada SIMANTAP untuk Deteksi Similarity dan Novelty Teks Akademik Berbasis NLP
DOI:
https://doi.org/10.70404/jikteks.v4i03.724Keywords:
GPT API, Natural Language Processing, Similarity Detection, Novelty Detection, Large Language Model, Semantic Similarity, Integritas AkademikAbstract
Digitalisasi dokumen akademik meningkatkan potensi kemiripan ide dan praktik plagiarisme yang tidak hanya berupa penyalinan langsung, tetapi juga parafrase dan penggantian sinonim. Sistem deteksi kemiripan yang tersedia umumnya hanya menghasilkan skor kemiripan tanpa menjelaskan posisi suatu penelitian terhadap penelitian terdahulu. Penelitian ini bertujuan menganalisis implementasi dan kemampuan GPT API dalam mendeteksi similarity dan novelty teks akademik pada aplikasi SIMANTAP, serta mengidentifikasi kebutuhan sistem, perspektif pengguna, dan implikasinya terhadap integritas akademik. Penelitian menggunakan pendekatan kuantitatif dengan metode pengembangan Waterfall. Sistem dibangun menggunakan PHP, Laravel, dan MySQL dalam bentuk pipeline analisis sembilan tahap yang mencakup ekstraksi teks, segmentasi dokumen menjadi chunk, ekstraksi kata kunci berbasis GPT, pencarian dokumen pembanding internal dan eksternal, pembangkitan embedding, perhitungan cosine similarity antar-chunk, agregasi skor, hingga analisis kebaruan kontekstual. Pengujian kebutuhan dilakukan dengan black-box testing, pengujian keluaran terhadap 29 dokumen proposal lintas domain, dan evaluasi persepsi terhadap lima dosen menggunakan kuesioner skala Likert. Seluruh kebutuhan dinyatakan valid, dengan similarity score rata-rata 36,09% (SD 24,33) dan novelty score rata-rata 58,07% (SD 9,92). Kalibrasi menunjukkan ambang konvensional 0,85 menghasilkan similarity index 0% pada dokumen yang relevan secara tematik sehingga ambang dikalibrasi ke 0,60. Evaluasi pengguna memperoleh nilai 91,2% berkategori Sangat Baik.
Downloads
References
S. Purwaningrum, A. Susanto, and A. Kristiningsih, “Pengaruh Synonym Recognition dalam Deteksi Kemiripan Teks Menggunakan Winnowing dan Cosine Similarity”, doi: 10.22146/jnteti.v12i3.6375.
N. Tamim Syuja’i, D. Imanuel Daeli, I. Alfarizi Darnela, E. A. Thio Candra, and J. Putra Tanjung, “Deteksi Plagiarisme Tugas Mahasiswa Menggunakan Sentence Embedding Berbasis Transformer dan Metode Cosine Similarity,” Jurnal Algoritma, vol. 23, no. 1, May 2026, doi: 10.33364/algoritma/v.23-1.3523.
S. Pudasaini, L. Miralles-Pechuán, D. Lillis, and M. L. Salvador, “Survey on Plagiarism Detection in Large Language Models: The Impact of ChatGPT and Gemini on Academic Integrity,” Jun. 2024, [Online]. Available: http://arxiv.org/abs/2407.13105
S. Agustian, “PENDEKATAN SEMANTIK DALAM DETEKSI BERBAGAI TIPE PLAGIARISME PADA DOKUMEN TEKS,” JURNAL TEKNIK INFORMATIKA, vol. 14, no. 2, pp. 101–114, Oct. 2021, doi: 10.15408/jti.v14i2.22841.
Salman, “SISTEM PENDETEKSI KEMIRIPAN JUDUL SKRIPSI BERBASIS WEB MENGGUNAKAN NLP DAN WORD EMBEDDINGS”, doi: 10.59818/jpi.v5i5.1964.
S. L. Rahma and U. Taufiq, “Analisis Tingkat Akurasi Metode Pendeteksian Plagiarisme Ide dengan Menggunakan Yake dan Sentence Transformer,” Journal of Internet and Software Engineering, vol. 5, no. 1, 2024, doi: https://doi.org/10.22146/jise.v5i1.9073.
J. P. Wahle, T. Ruas, F. Kirstein, and B. Gipp, “How Large Language Models are Transforming Machine-Paraphrased Plagiarism,” Nov. 2022, doi: 10.18653/v1/2022.emnlp-main.62.
J. Lee, T. Le, J. Chen, and D. Lee, “Do Language Models Plagiarize?,” in ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023, Association for Computing Machinery, Inc, Apr. 2023, pp. 3637–3647. doi: 10.1145/3543507.3583199.
M. Ostendorff, T. Blume, T. Ruas, B. Gipp, and G. Rehm, “Specialized document embeddings for aspect-based similarity of research papers,” in Proceedings of the ACM/IEEE Joint Conference on Digital Libraries, Institute of Electrical and Electronics Engineers Inc., Jun. 2022. doi: 10.1145/3529372.3530912.
T. Ghosal, T. Saikh, T. Biswas, A. Ekbal, and P. Bhattacharyya, “Novelty Detection: A Perspective from Natural Language Processing under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license,” Computational Linguistics, vol. 48, no. 1, 2022, doi: 10.1162/COLI.
D. Wardani and C. Achmad, “SSTI: Semantic Similarity to detect Novelty of Thesis Ideas,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Nov. 2022, pp. 376–381. doi: 10.1145/3575882.3575955.
T. B. Brown et al., “Language Models are Few-Shot Learners,” Jul. 2020, doi: 10.48550/arXiv.2005.14165.
P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, “Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing,” ACM Comput. Surv., vol. 55, no. 9, Sep. 2023, doi: 10.1145/3560815.
S. A. Atmaja, A. W. R. Emanuel, and Suyoto, “A Systematic Literature Review on Intelligent Optimization for Virtual Machine Allocation in Cloud Data Centers,” in ICCSIT 2025 - Proceedings of the 2025 18th International Conference on Computer Science and Information Technology, Association for Computing Machinery, Inc, Mar. 2026, pp. 58–68. doi: 10.1145/3783862.3783871.
J. Budiasto, “Advancements in Machine Learning Algorithms for Big Data Analytics,” Journal of Hunan University Natural Sciences, Mar. 2026, doi: 10.55463/issn.1674-2974.53.2.5.
E. Kasneci et al., “ChatGPT for good? On opportunities and challenges of large language models for education,” Learn. Individ. Differ., vol. 103, p. 102274, Apr. 2023, doi: 10.1016/J.LINDIF.2023.102274.
W. Castillo-González, C. O. Lepez, and M. C. Bonardi, “Chat GPT: a promising tool for academic editing,” Data and Metadata, vol. 1, Oct. 2022, doi: 10.56294/dm202223.
H. Steck, C. Ekanadham, and N. Kallus, “Is Cosine-Similarity of Embeddings Really About Similarity?,” in WWW 2024 Companion - Companion Proceedings of the ACM Web Conference, Association for Computing Machinery, Inc, May 2024, pp. 887–890. doi: 10.1145/3589335.3651526.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Raafi Syarahil Azhar, Subhanjaya Angga Atmaja, Yasri
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
