SISTEM PERINGKAS TEKS OTOMATIS MULTI DOKUMEN KLIPING ARTIKEL BERITA GEMPA MENGGUNAKAN METODE TF-IDF



Abstract
New technology is increasingly evolving so that internet users can find out the news on the internet quickly. Most news stories about the earthquake make it difficult for readers to know the news contents in depth. Because of this, summarizing multi-document texts is important. So that readings are fast and easy and information can be obtained briefly. With the summarization of the text the reader can know the clippings of earthquake news briefly not only from one document but several documents or multiple documents can be done, at least from two documents. The author constructs a prototype multi-document text summarizing system using the term frequency inverse document frequency (TF-IDF) method for breaking the content of documents into sentences, discarding characters, breaking sentences into words, giving weight values to words, adding weight values, measuring idf and TF values -IDF in order to obtain the word weight value of each sentence, t Each document's summary is merged and summarized again, so as to become the third summary as a combination of two documents. Web-based tools are used, the programming language used is PHP and MySQL DBMS. This application can implement multi-document automatic text summarizing news article clippings on the internet TF-IDF method. This system can help find out the important contents of many news article clippings on the internet. the system has the accuracy of the results of the respondent's test 54.45% and the similarity test document accuracy is 78,023%
Keywords: clipping news article, text summary multi document, TF-IDFCITATIONS
PDF Downloads
Metrics
References
[2] F. Hendy Evan and Y. W. Sigit Purnomo, Pembangunan Perangkat Lunak Peringkas Dokumen dari Banyak Sumber Menggunakan Sentence Scoring dengan Metode TF-IDF, Semin. Nas. Apl. Teknol. Inf. Yogyakarta, vol. 21, no. 17, pp. 1907–5022, 2014.
[3] A. Z. Z. Abidin and E. Y. Rayi, PERINGKAS TEKS OTOMATIS DOKUEM TUNGGAL DAN MULTI BAHASA MENGGUNAKAN METODE TF-IDF, 2019.
[4] A. Z. Z. Abidin, Y. Murdianingsih, U. T. Suryadi, and D. Setiyadi, TEXT SUMMARIZING SYSTEM OF ENGLISH SUBJECTS AND TEXT MINING SUBJECTS, vol. 7, no. 5, pp. 730–742, 2020.
[5] W. Yulita, S. Priyanta, and A. SN, Automatic Text Summarization Based on Semantic Networks and Corpus Statistics, IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 13, no. 2, p. 137, 2019.
[6] V. Amrizal, Penerapan Metode Term Frequency Inverse Document Frequency (Tf-Idf) Dan Cosine Similarity Pada Sistem Temu Kembali Informasi Untuk Mengetahui Syarah Hadits Berbasis Web (Studi Kasus: Hadits Shahih Bukhari-Muslim), J. Tek. Inform., vol. 11, no. 2, pp. 149–164, 2018.
[7] N. Hayatin, C. Fatichah, and D. Purwitasari, Trending Issue Untuk Peringkasan Multi Dokumen, vol. 13, pp. 38–44, 2015.
[8] A. Widiantoro, Peringkasan Teks Otomatis Pada Dokumen Berbahasa Jawa Menggunakan Metode Tf-Idf, 2014.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Aa Zezen Zaenal Abidin, Enung Nurjanah

This work is licensed under a Creative Commons Attribution 4.0 International License.
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on http://creativecommons.org/licenses/by/4.0/.