Media Sentiment Analysis of East Java Province: Lexicon-Based vs Machine Learning

Ikhwan Rustanto, Nur Aini Rakhmawati

Abstract


Indonesian Ministry of Communication and Informatics reported internet users in Indonesia reached 150 million with a penetration of 56% in January 2019. This indicates the era of information disclosure; therefore, information on government performance is more easily obtained by all levels of society. Society is becoming more sensitive to government performance, and more feedback is being given to the government. This large amount of feedback has stimulated research on public sentiment analysis. This study compares the public sentiment analysis by two different approaches to the government performance of East Java Province. The study was comparing the lexicon-based method approach and the Support Vector Machine (SVM) from the machine learning approach. This study uses Twitter and Instagram datasets, and also the online news media web that reports on East Java. This study found that by using a combined data source of social media and online media, the lexicon-based approach produced an accuracy value of 57.7%; while the SVM machine learning method approach produces an accuracy of 44.7%.

Keywords


East Java; Lexicon-Based; Sentiment Analysis; Support Vector Machine

Full Text:

PDF

References


“OTDA Kemendagri,” Jumlah Provinsi, Kab, Dan Kota, 2018. https://otda.kemendagri.go.id/seputar-otda/jumlah-provinsi-kab-dan-kota/ (accessed Nov. 02, 2018).

“Kementerian Komunikasi dan Informatika.,” Jumlah Pengguna Internet 2017 Meningkat, Kominfo Terus Lakukan Percepatan Pembangunan Broadband, 2018. https://kominfo.go.id/index.php/content/detail/12640/siaran-pers-no-53hmkominfo022018-tentang-jumlah-pengguna-internet-2017-meningkat-kominfo-terus-lakukan-percepatan-pembangunan-broadband/0/siaran_pers (accessed Nov. 02, 2018).

O. Shepelenko, "Opinion Mining and Sentiment Analysis using Bayesian and Neural Networks Approaches," 2017.

W. Medhat, A. Hassan, and H. Korashy, "Sentiment analysis algorithms and applications: A survey," Ain Shams Eng. J. vol. 5, no. 4, pp. 1093–1113, 2014.

D. Osimo and F. Mureddu, "Research challenge on opinion mining and sentiment analysis," Univ. Paris-Sud Lab. LIMSI-CNRS Bâtim., vol. 508, 2012.

T. Wilson, J. Wiebe, and P. Hoffmann, "Recognizing contextual polarity in phrase-level sentiment analysis," 2005.

S. Baccianella, A. Esuli, and F. Sebastiani, "Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining.,"

in LREC, 2010, vol. 10, pp. 2200–2204.

I. Kusumawati, E. W. Pamungkas, S. Kom, and M. Kom, “Analisa Sentimen Menggunakan Lexicon Based Untuk Melihat Persepsi Masyarakat Terhadap Kenaikan Harga Rokok Pada Media Sosial Twitter,” PhD Thesis, Universitas Muhammadiyah Surakarta, 2017.

D. Rosdiansyah, “Analisis Sentimen Twitter Menggunakan Metode K-Nearest Neighbor dan Pendekatan Lexicon,” PhD Thesis, Universitas Islam Negeri Sultan Syarif Kasim Riau, 2014.

G. A. Buntoro, T. B. Adji, and A. E. Purnamasari, "Sentiment Analysis Twitter Dengan Kombinasi Lexicon Based Double dan Propagation," CITEE 2014, pp. 39–43, 2014.

M. M. Munir, M. Fauzi, and R. Perdana, “Implementasi metode backpropagation neural network berbasis lexicon based features dan

bag of words untuk identifikasi ujaran kebencian pada twitter,” 2018.

E. Indrayuni, “Analisa Sentimen Review Hotel Menggunakan Algoritma Support Vector Machine Berbasis Particle Swarm Optimization,” EVOLUSI-J. Sains Dan Manaj. AMIK BSI Purwok., vol. 4, no. 2, 2016.

N. Y. Faradhillah, R. P. Kusumawardani, and I. Hafidz, “Eksperimen Sistem Klasifikasi Analisa Sentimen Twitter pada Akun Resmi Pemerintah Kota Surabaya Berbasis Pembelajaran Mesin,” SESINDO 2016, vol. 2016, 2016.

D. N. Devi, C. K. Kumar, and S. Prasad, "A feature-based approach for sentiment analysis by using support vector machine," in Advanced Computing (IACC), 2016 IEEE 6th International Conference on, 2016, pp. 3–8.




DOI: http://dx.doi.org/10.12962/j23546026.y2020i6.11094

Refbacks

  • There are currently no refbacks.


View my Stat: Click Here

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