Analisis Sentimen Data Twitter Tentang Pasangan Capres-Cawapres Pemilu 2019 Dengan Metode Lexicon Based Dan Support Vector Machine

Danar Wido Seno, Arief Wibowo

Abstract


Social media writing content growing make a lot of new words that appear on Twitter in the form of words and abbreviations that appear so that sentiment analysis is increasingly difficult to get high accuracy of textual data on Twitter social media. In this study, the authors conducted research on sentiment analysis of the pairs of candidates for President and Vice President of Indonesia in the 2019 Elections. To obtain higher accuracy results and accommodate the problem of textual data development on Twitter, the authors conducted a combination of methods to conduct the sentiment analysis with unsupervised and supervised methods. namely Lexicon Based. This study used Twitter data in October 2018 using the search keywords with the names of each pair of candidates for President and Vice President of the 2019 Elections totaling 800 datasets. From the study with 800 datasets the best accuracy was obtained with a value of 92.5% with 80% training data composition and 20% testing data with a Precision value in each class between 85.7% - 97.2% and Recall value for each class among 78, 2% - 93.5%. With the Lexicon Based method as a labeling dataset, the process of labeling the Support Vector Machine dataset is no longer done manually but is processed by the Lexicon Based method and the dictionary on the lexicon can be added along with the development of data content on Twitter social media.


Keywords


Sentiment Analysis; Support Vector Machine, Lexicon Based; Twitter Sentiment Analysis; Sentiment Analysis with R Programming

Full Text:

PDF

References


Y. Setyanto, “Media Sosial sebagai Sarana Komunikasi Perusahaan dengan Media Media Sosial sebagai Sarana Komunikasi Perusahaan dengan Media,” no. September, 2016.

G. Vinodhini, “Sentiment Analysis and Opinion Mining : A Survey,” vol. 2, no. 6, 2012.

P. Nomleni, “Sentiment Analysis Menggunakan Support Vector Machine ( SVM ),” 2015.

D. Maulina, R. Sagara, I. Komputer, and J. R. Utara, “Klasifikasi Artikel Hoax Menggunakan Support Vector Machine Linear Dengan Pembobotan Term Frequency–Inverse Document,” vol. 2, no. 1, pp. 35–40, 2018.

N. Muchammad, S. Hadna, and P. I. Santosa, “Studi Literatur Tentang Perbandingan Metode Untuk Proses Analisis Sentimen di Twitter,” no. March, 2016.

Nurhuda, F. and Sihwi, S. W. (2014) ‘Analisis Sentimen Masyarakat terhadap Calon Presiden Indonesia 2014 berdasarkan Opini dari Twitter Menggunakan Metode Naive Bayes Classifier’, Jurnal ITSMART, 2.

N. Vyrva, “Sentiment Analysis in Social Media,” 2016.

F. M. Matulatuwa, E. Sediyono, and A. Iriani, “Text Mining Dengan Metode Lexicon Based Untuk Sentiment Analysis Pelayanan PT . POS Indonesia Melalui Media Sosial Twitter,” vol. 2, no. 3, p. 5093, 2017.

G. A. Buntoro, “Analisis Sentimen Calon Gubernur DKI Jakarta 2017 Di Twitter,” Integer J., vol. 1, no. 1, pp. 32–41, 2017.

Imam Syafei dan Hendri Murfi, “Analisis Kinerja Kombinasi Metode Berbasis Lexicon dan Metode Berbasis Learning pada Analisis Sentimen Twitter” FMIPA UI, 2014.

Purba, I. D. C., Hidayati, H. and Gozali, A. A. (2014) ‘Metode Holistic Lexicon-Based Untuk Analisis Sentiment Pada Dokumen Bahasa Indonesia (Studi Kasus: Tweets Mengenai Isu Sosial Kota Bandung)’, Telkom University.




DOI: http://dx.doi.org/10.22441/fifo.2019.v11i2.004

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 Jurnal Ilmiah FIFO



Jurnal Ilmiah FIFO
Fakultas Ilmu Komputer
Universitas Mercu Buana
Jl. Raya Meruya Selatan, Kembangan, Jakarta 11650
Tlp./Fax: +62215871335
p-ISSN: 2085-4315
e-ISSN: 2502-8332
http://publikasi.mercubuana.ac.id/index.php/fifo

e-mail:fifo.journal@mercubuana.ac.id

  Creative Commons Licence 
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

 

width= width=

Image result for jurnal sinta