Sistem Ringkasan Dokumen Otomatis Berbasis Word2Vec dan Support Vector Machine
DOI:
https://doi.org/10.29407/8s6y9795Keywords:
Confusion Matrix, Ringkasan Dokumen, ROUGE, Support Vector Machine, Word2VecAbstract
Perkembangan informasi digital menyebabkan peningkatan jumlah dokumen teks yang harus dipahami secara cepat dan efisien. Hal ini mendorong perlunya sistem ringkasan dokumen otomatis untuk membantu pengguna memperoleh inti informasi tanpa membaca keseluruhan dokumen. Penelitian ini bertujuan untuk membangun sistem ringkasan dokumen otomatis berbasis pembelajaran mesin menggunakan metode Word2Vec dan Support Vector Machine (SVM). Word2Vec digunakan untuk merepresentasikan setiap kalimat ke dalam bentuk vektor numerik yang menangkap hubungan semantik antar kata, sedangkan SVM digunakan untuk mengklasifikasikan kalimat penting dan tidak penting dalam dokumen. Proses peringkasan dilakukan dengan memilih kalimat-kalimat yang diklasifikasikan sebagai kalimat penting untuk membentuk ringkasan akhir. Pengujian sistem dilakukan pada kumpulan dokumen teks dengan membandingkan ringkasan hasil sistem terhadap ringkasan referensi menggunakan metrik evaluasi ROUGE. Hasil pengujian menunjukkan bahwa kombinasi Word2Vec dan SVM mampu menghasilkan ringkasan yang representatif dan relevan terhadap isi dokumen asli.
Downloads
References
[1] K. Kurniawan and S. Louvan, “IndoSum: A New Benchmark Dataset for Indonesian Text Summarization,” Proceedings of the 2018 International Conference on Asian Language Processing, IALP 2018, pp. 215–220, Oct. 2018, doi: 10.1109/IALP.2018.8629109.
[2] M. A. Hedderich, L. Lange, H. Adel, J. Strötgen, and D. Klakow, “A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios,” NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, pp. 2545–2568, 2021, doi: 10.18653/V1/2021.NAACL-MAIN.201.
[3] A. Cemiloglu et al., “Support Vector Machine (SVM) Application for Uniaxial Compression Strength (UCS) Prediction: A Case Study for Maragheh Limestone,” Applied Sciences 2023, Vol. 13, Page 2217, vol. 13, no. 4, p. 2217, Feb. 2023, doi: 10.3390/APP13042217.
[4] M. Mars, “From Word Embeddings to Pre-Trained Language Models: A State-of-the-Art Walkthrough,” Applied Sciences 2022, Vol. 12, Page 8805, vol. 12, no. 17, p. 8805, Sep. 2022, doi: 10.3390/APP12178805.
[5] S. Sathyanarayanan, “Confusion Matrix-Based Performance Evaluation Metrics,” African Journal of Biomedical Research, pp. 4023–4031, Nov. 2024, doi: 10.53555/AJBR.V27I4S.4345.
[6] A. Al Foysal and R. Böck, “Who Needs External References?—Text Summarization Evaluation Using Original Documents,” AI 2023, Vol. 4, Pages 970-995, vol. 4, no. 4, pp. 970–995, Nov. 2023, doi: 10.3390/AI4040049.
[7] P. Ayuningtiyas, K. D. Tania, and W. K. Sari, “Sentiment-Based Knowledge Discovery pada Aplikasi iPusnas Menggunakan Metode Machine Learning dan Deep Learning,” Journal of Applied Informatics and Computing, vol. 9, no. 5, pp. 2486–2497, Oct. 2025, doi: 10.30871/JAIC.V9I5.10258.
[8] X. Rong, “word2vec Parameter Learning Explained,” Nov. 2014, Accessed: Dec. 19, 2025. [Online]. Available: https://arxiv.org/pdf/1411.2738
[9] J. Li, J. Wang, and E. Xue, “Applying a Support Vector Machine (SVM-RFE) Learning Approach to Investigate Students’ Scientific Literacy Development: Evidence from Asia, Europe, and South America,” Journal of Intelligence 2024, Vol. 12, Page 111, vol. 12, no. 11, p. 111, Nov. 2024, doi: 10.3390/JINTELLIGENCE12110111.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mochamad Hafid, Muhamad Aldi Hawari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants 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 acknowledgment 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 acknowledgment 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
