Kalibrasi Ambang Batas Kemiripan TF IDF dan Cosine Similarity untuk Deteksi Duplikasi Judul Pengabdian kepada Masyarakat pada Teks Pendek

Zurnan Alfian; Asep Erlan Maulana; Syaeful Machfud

doi:10.35447/jitekh.v14i2.1585

Authors

Zurnan Alfian Universitas Pamulang, Tangerang Selatan
Asep Erlan Maulana Universitas Pamulang, Tangerang Selatan
Syaeful Machfud Universitas Pamulang, Tangerang Selatan

DOI:

https://doi.org/10.35447/jitekh.v14i2.1585

Keywords:

Cosine Similarity, Flask, Community Service, Literary, TF-IDF

Abstract

Community Service (PkM) activities constitute a vital pillar of the higher education "Tridharma" (Three Pillars of Higher Education), serving to apply students' technological competencies to address social issues. However, the surge in PkM proposals each semester has created serious administrative challenges, specifically the high frequency of topic repetition and duplication. The manual verification process currently conducted by supervising lecturers faces constraints regarding memory limitations, time inefficiency, and the risk of subjectivity. This research aims to design, implement, and test a web-based automated PkM title selection system utilizing a combination of Natural Language Processing and Information Retrieval. The methodology involves five text preprocessing stages (case folding, cleaning, tokenizing, stopword removal, and stemming using the Sastrawi stemmer), Term Frequency-Inverse Document Frequency (TF-IDF) feature weight extraction, and vector angular distance calculation using Cosine Similarity. The system was developed using the Flask micro-web framework and an SQLite database, implemented in Python 3.11.9. Experiments were conducted on a primary dataset of 839 PkM titles from Informatics Engineering students at Universitas Pamulang (comprising a reference corpus of 641 approved titles and a test set of 198 rejected titles). Threshold tuning established three decision zones: Highly Similar/Saturated (≥0.80), Partially Similar (0.60–0.79), and Unique/Eligible (<0.60). Classification performance testing against expert ground truth yielded an Accuracy of 95.6%, Precision of 92.8%, Recall of 84.5%, and an F1-Score of 88.4%, significantly exceeding the study's minimum key performance indicator (≥85%). The system proved effective as a digital reference for the selection process, reducing verification time and ensuring the originality of student PkM innovation outputs

Downloads

Download data is not yet available.

References

M. Azmi, "Analisis Tingkat Plagiasi Dokumen Skripsi Dengan Metode Cosine Similarity Dan Pembobotan TF-IDF," TEKNIMEDIA: Teknologi Informasi dan Multimedia, vol. 2, no. 2, pp. 90-95, 2022. DOI: https://doi.org/10.46764/teknimedia.v2i2.51.

A. A. Huda, R. Fajarudin, and A. Hadinegoro, "Sistem Rekomendasi Content-based Filtering Menggunakan TF-IDF Vector Similarity Untuk Rekomendasi Artikel Berita," BITS: Building of Informatics, Technology and Science, vol. 4, no. 3, pp. 123-130, 2022. DOI: https://doi.org/10.47065/bits.v4i3.2511.

A. M. R. Haz and A. N. Rohman, "Sistem Rekomendasi Berita dengan Metode Content-Based Filtering," JIKA (Jurnal Informatika), vol. 9, no. 2, pp. 143-150, 2025. DOI: https://doi.org/10.31000/jika.v9i2.13247.

W. Tanuwijaya, C. E. Setiawan, H. Irsyad, and A. Rahman, "Implementasi TF-IDF dan Cosine Similarity untuk Penyaringan Dokumen Berita," Device: Journal of Information System and Computer Science, vol. 6, no. 2, pp. 1-10, 2025. DOI: https://doi.org/10.46576/device.v6i2.6724.

S. Pawestri, dkk., "Analisis Perbandingan Metode Jaccard Coefficient dan Cosine Similarity untuk Kemiripan Teks," Majalah Ilmiah Informatika dan Komputer (MIB), vol. 8, no. 1, pp. 477-487, 2024. DOI: https://doi.org/10.30865/mib.v8i1.7109.

A. Pratomo and E. Utami, "Analisis dan Implementasi Content-Based Filtering dengan Cosine Similarity untuk Sistem Rekomendasi Tugas Akhir Mahasiswa," AITI: Jurnal Teknologi Informasi, vol. 23, no. 2, pp. 319-333, 2026. DOI: https://doi.org/10.24246/aiti.v23i2.319-333.

S. A. Gilbert and M. I. Sulistyo, "Analisis Sentimen Berdasarkan Ulasan Pengguna Aplikasi MYPERTAMINA Pada Google Playstore Menggunakan Metode Naive Bayes," STORAGE: Jurnal Ilmiah Teknik Dan Ilmu Komputer, vol. 2, no. 3, pp. 100-108, 2023. DOI: https://doi.org/10.55123/storage.v2i3.2333.

D. F. Surianto, "Enhancing K-Means Clustering for Journal Articles using TF-IDF and LDA Feature Extraction," Brilliance: Research of Artificial Intelligence, vol. 4, no. 2, pp. 964-972, 2024. DOI: https://doi.org/10.47709/brilliance.v4i2.5547.

A. N. Rohman, M. N. Fauzy, and A. Sa’di, "Sistem Rekomendasi Buku Menggunakan Algoritma Rabin-Karp," Jurnal Eksplora Informatika, vol. 12, no. 1, pp. 86-94, 2024. DOI: https://doi.org/10.30864/eksplora.v12i1.1074.

K. R. Sari, W. Suharso, and Y. Azhar, "Pembuatan Sistem Rekomendasi Film dengan Menggunakan Metode Item Based Collaborative Filtering pada Apache Mahout," Jurnal Repositor, vol. 2, no. 6, pp. 815-824, 2024. DOI: https://doi.org/10.22219/repositor.v2i6.30715.

H. Santoso and M. R. Anwar, "Penerapan Pembobotan TF-IDF untuk Deteksi Plagiasi Dokumen Akademik," Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 1, pp. 112-119, 2023. DOI: https://doi.org/10.29207/resti.v7i1.3501.

R. K. Wibowo and A. P. Wibawa, "Optimasi Pra-pemrosesan Teks Bahasa Indonesia Menggunakan Pustaka Sastrawi pada Analisis Sentimen," Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 9, no. 3, pp. 501-510, 2022. DOI: https://doi.org/10.25126/jtiik.2022934051.

D. S. Maulana and I. K. Raharjana, "Implementasi Cosine Similarity untuk Penilaian Kesesuaian Topik Proposal Penelitian," Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI), vol. 12, no. 2, pp. 145-152, 2023. DOI: https://doi.org/10.22146/jnteti.v12i2.4502.

F. R. Hariri and T. A. Putri, "Sistem Temu Balik Informasi Dokumen Teks Menggunakan VSM dan TF-IDF," KINETIK: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, vol. 7, no. 4, pp. 315-322, 2022. DOI: https://doi.org/10.22219/kinetik.v7i4.1405.

A. B. Setiawan and C. E. Widyastuti, "Komparasi Kinerja Algoritma Klasifikasi Teks Berbasis TF-IDF pada Kumpulan Abstrak Jurnal," Jurnal Sistem Informasi Bisnis (JSIB), vol. 13, no. 1, pp. 45-53, 2023. DOI: https://doi.org/10.21456/vol13iss1pp45-53.

T. M. Akhriza and A. W. Yulianto, "Penggunaan Algoritma Cosine Similarity pada Sistem Deteksi Kemiripan Teks Laporan Praktikum," Jurnal Edukasi dan Penelitian Informatika (JEPIN), vol. 9, no. 2, pp. 210-218, 2023. DOI: https://doi.org/10.26418/jp.v9i2.50123.

S. Y. Yulianti and R. R. Fadilla, "Penerapan Cosine Similarity dan TF-IDF untuk Sistem Rekomendasi Jurnal Ilmiah," Jurnal Sistim Informasi dan Teknologi, vol. 5, no. 3, pp. 110-117, 2023. DOI: https://doi.org/10.37034/jsisfotek.v5i3.220.

Y. D. Prabowo and H. B. Santoso, "Analisis Perbandingan Ekstraksi Fitur TF-IDF dan Word2Vec pada Deteksi Kemiripan Dokumen," Jurnal Buana Informatika, vol. 15, no. 1, pp. 32-40, 2024. DOI: https://doi.org/10.24002/jbi.v15i1.7501.

M. A. Fauzi and S. R. Wardhani, "Pemanfaatan Scikit-Learn dan NLTK untuk Analisis Kemiripan Teks pada Dokumen Bahasa Indonesia," Jurnal Ilmu Komputer dan Informasi (JIKI), vol. 16, no. 2, pp. 101-109, 2023. DOI: https://doi.org/10.21609/jiki.v16i2.1105.

B. A. Prakoso and D. N. P. Ningrum, "Pengaruh Text Preprocessing terhadap Kinerja Algoritma Cosine Similarity dalam Analisis Teks," Sinkron: Jurnal dan Penelitian Teknik Informatika, vol. 8, no. 3, pp. 1500-1510, 2024. DOI: https://doi.org/10.33395/sinkron.v8i3.13500.

D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed. draft. Pearson Education, 2022.

G. Salton and M. J. McGill, Introduction to Modern Information Retrieval. New York: McGraw-Hill, 1986.

N. V. A. E. Putri and N. M. A. W. Dewi, "PDF Plagiarism Detection System Using Cosine Similarity," Jurnal Sains, Sistem, dan Teknologi Komputer (JSSTK), vol. 3, no. 1, pp. 1-10, 2025. DOI: https://doi.org/10.24912/jsstk.v3i1.37103

D. Iskandar and A. Kurniawati, "Analisis Perbandingan Teknik Word2vec dan Doc2vec dalam Mengukur Kemiripan Dokumen Menggunakan Cosine Similarity," Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 12, no. 1, pp. 133-144, 2025. DOI: https://doi.org/10.25126/jtiik.20251219143

S. A. S. Mola, Y. C. Luttu, and D. N. Rumlaklak, "Perbandingan Metode Machine Learning dalam Analisis Sentimen Komentar Pengguna Aplikasi InDriver pada Dataset Tidak Seimbang," Jurnal Sistem Informasi Bisnis, vol. 14, no. 3, pp. 247-255, 2024. DOI: https://doi.org/10.21456/vol14iss3pp247-255

D. L. Girsang, A. Sidiq, and T. S. Elenaputri, "Analisis Sentimen Masyarakat terhadap Layanan BPJS Kesehatan dan Faktor-Faktor Pendukung Opini dengan Pemodelan Natural Language Processing (NLP)," Emerging Statistics and Data Science Journal, vol. 1, no. 2, pp. 238-249, 2023. DOI: https://doi.org/10.20885/esds.vol1.iss.2.art24