PENGGUNAAN FITUR WORDCLOUD DAN DOCUMENT TERM MATRIX DALAM TEXT MINING

  • Musthofa Galih Pradana Universitas Alma Ata

Abstract

Much information and data can be extracted from social media differences, with more and more social media users. Data in 2019 states that there are 150 million users of social media in Indonesia. Based on the number of active users of social media, it can be exploited for deeper information extraction and analysis. One way that can be done is by taking comment data on social media for further processing or mining. In this research, we do data crawling and utilize the Term Document Matrix and Word Cloud features to find the most frequently written words on Facebook and Twitter social media. The words that appear most often based on the Word Cloud feature will be analyzed to infer from words written on social media. In this study the word that often appears on Facebook is the word garuda for 3621 words and on Twitter is the Indonesian word for 1572. On the Facebook platform the resulting word has a positive tendency because the topics discussed are still around airlines, while on Twitter it has a negative tendency because of the word what appears is a personal name that has a negative tendency for the company.

References

[1] V. Kale, “Enterprise performance intelligence and decision patterns,” Enterp. Perform. Intell. Decis. Patterns, pp. 1–262, 2017, doi: 10.4324/9781351228428.
[2] D. Saputra, B. Pratama, Y. Akbar, W. G.-C. O. SPOT, and undefined 2018, “Penerapan Text Mining Untuk Assingment Complaint Handling Customer Terhadap Divisi Terkait Menggunakan Metode Decission,” Jurnal.Stikomcki.Ac.Id, vol. 11, no. 2, pp. 207–216, 2018.
[3] M. Nurjannah and I. Fitri Astuti, “PENERAPAN ALGORITMA TERM FREQUENCY-INVERSE DOCUMENT FREQUENCY (TF-IDF) UNTUK TEXT MINING Mahasiswa S1 Program Studi Ilmu Komputer FMIPA Universitas Mulawarman Dosen Program Studi Ilmu Komputer FMIPA Universitas Mulawarman,” J. Inform. Mulawarman, vol. 8, no. 3, pp. 110–113, 2013.
[4] R. Siringoringo, “Text Mining dan Klasterisasi Sentimen Pada Ulasan Produk Toko Online,” Tek. Inform. Univ. Prima Indones. Medan, vol. 2, pp. 1–6, 2019.
[5] M. Yasid, “Analisis Sentimen Maskapai Citilink Pada Twitter Dengan Metode Naãve Bayes,” J. Ilm. Inform., vol. 7, no. 02, p. 82, 2019, doi: 10.33884/jif.v7i02.1329.
[6] 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, doi: 10.30865/komik.v3i1.1697.
[7] T. S. Kartikasari et al., “IMPLEMENTASI TEXT MINING UNTUK ANALISIS OPINI PUBLIK TERHADAP CALON PRESIDEN,” vol. 7, no. 1, 2018.
[8] N. L. Ratniasih, M. Sudarma, and N. Gunantara, “Penerapan Text Mining Dalam Spam Filtering Untuk Aplikasi Chat,” Maj. Ilm. Teknol. Elektro, vol. 16, no. 3, p. 13, 2017, doi: 10.24843/mite.2017.v16i03p03.
[9] F. Abdurrahman, M. Irfan, R. Andrian, J. A. H. N. No, and K. Bandung, “Implementasi Algoritma TF-IDF untuk Pencarian Pedoman Akademik dan Penentuan Sanksi Pada Jurusan Teknik Informatika UIN Sunan Gunung Djati Bandung,” Insight, vol. 1, no. 1, pp. 133–140, 2017.
Published
2020-03-18
How to Cite
PRADANA, Musthofa Galih. PENGGUNAAN FITUR WORDCLOUD DAN DOCUMENT TERM MATRIX DALAM TEXT MINING. JURNAL ILMIAH INFORMATIKA, [S.l.], v. 8, n. 01, p. 38-43, mar. 2020. ISSN 2615-1049. Available at: <http://ejournal.upbatam.ac.id/index.php/jif/article/view/1838>. Date accessed: 05 july 2020. doi: https://doi.org/10.33884/jif.v8i1.1838.