Penerapan Algoritma Text Mining, Steaming Dan Texrank Dalam Peringkasan Bahasa Inggris

Leni Pertiwi

Leni Pertiwi * Universitas Budi Darma, Medan, Indonesia

(*) Corresponding Author

Keywords: Text Summarization; English; TextMining; Textrank; Text

Abstract

Text summarization in English is used to summarize a text using a computer to get a summary of the text. The text summarization method uses extractives because this method takes important information from a text without changing it or the information. One of the algorithms that can be used to summarize text in English is by using the TextRank algorithm. The advantage of the TextRank algorithm is that it does not require in-depth knowledge of a language and does not require training data to be able to summarize text. The way this algorithm works is to represent sentences in the text into a graph, calculating the value of each sentence using questions (similarities) between sentences to determine the summary results. In addition to using similarity to determine important sentences, this study also uses a modified TextRank, namely by using levenshtein distance to calculate summaries by comparing the similarities between strings by entering, entering, or replacing character strings. Summarization of text in English using TextRank is done by summarizing 100 English texts which will then be evaluated using ROUGE. ROUGE evaluation works by comparing the summary results from TextRank with manual summaries by experts in the field of English. To facilitate the ranking requires a text mining algorithm, using text mining algorithms can be used to get actual results.

References

[1] D. Nurnaningsih and A. A. Permana, “Rancangan Aplikasi Pengamanan Data Dengan Algoritma Advanced Encyption Standard (Aes),” J. Tek. Inform., vol. 11, no. 2, pp. 177–186, 2018, doi: 10.15408/jti.v11i2.7811.
[2] P. Soepomo, “Penerapan Text Mining Pada Sistem Klasifikasi Email Spam Menggunakan Naive Bayes,” Penerapan Text Min. Pada Sist. Klasifikasi Email Spam Menggunakan Naive Bayes, vol. 2, no. 3, pp. 73–83, 2014, doi: 10.12928/jstie.v2i3.2877.
[3] I. WARMAN and R. RAMDANIANSYAH, “ANALISIS PERBANDINGAN KINERJA QUERY DATABASE MANAGEMENT SYSTEM (DBMS) ANTARA MySQL 5.7.16 DAN MARIADB 10.1,” J. Teknoif, vol. 6, no. 1, pp. 32–41, 2018, doi: 10.21063/jtif.2018.v6.1.32-41.
[4] Defta Afriani, “Perancangan Knowledge Management System dengan SECI Model Pada Layanan Perbaikan AC Mobil di Bengkel Agung Motor Cinere Menggunakan VB.NET,” Inform. SIMANTIK, vol. 4, no. 1, pp. 29–35, 2019.
[5] R. Melita et al., “( TF-IDF ) DAN COSINE SIMILARITY PADA SISTEM TEMU KEMBALI INFORMASI UNTUK MENGETAHUI SYARAH HADITS BERBASIS WEB ( STUDI KASUS : SYARAH UMDATIL AHKAM ),” vol. 11, no. 2, 2018.
[6] D. Andriani and M. T. Furqon, “Peringkasan Teks Otomatis Pada Artikel Berita Hiburan Berbahasa Indonesia Menggunakan Metode BM25,” vol. 3, no. 3, pp. 2603–2610, 2019.
[7] Suendri, “Implementasi Diagram UML (Unified Modelling Language) Pada Perancangan Sistem Informasi Remunerasi Dosen Dengan Database Oracle (Studi Kasus: UIN Sumatera Utara Medan),” J. Ilmu Komput. dan Inform., vol. 3, no. 1, pp. 1–9, 2018, [Online]. Available: http://jurnal.uinsu.ac.id/index.php/algoritma/article/download/3148/1871.
[8] Y. Heriyanto, “Perancangan Sistem Informasi Rental Mobil Berbasis Web Pada PT.APM Rent Car,” J. Intra-Tech, vol. 2, no. 2, pp. 64–77, 2018.
[9] E. Z. Henry Februariyanti, “Rancang Bangun Sistem Perpustakaan untuk Jurnal Elektronik,” J. Teknol. Inf. Din., vol. 17, no. 2, pp. 124–132, 2012.
[10] M. P. Simatupang and D. P. Utomo, “Analisa Testimonial Dengan Menggunakan Algoritma Text Mining Dan Term Frequency-Inverse Document Frequence (Tf-Idf) Pada Toko Allmeeart,” KOMIK (Konferensi Nas. Teknol. Inf. dan Komputer), vol. 3, no. 1, pp. 808–814, 2019.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Penerapan Algoritma Text Mining, Steaming Dan Texrank Dalam Peringkasan Bahasa Inggris