Online Transportation Sentiment Analysis Using Support Vector Machine Based on Particle Swarm Optimization
Abstract
Phenomenon of online transportation with some problems like crime and fraud in Indonesia triggers pros and cons to Twitter users. This study aims to find out sentiments of the society on online transportation and compare the accuracy of SVM and SVM-PSO with default parameters value. The proposed solution divided the dataset into training and testing data, because some researches only used one dataset that had already been classified. The research data is tweet data, which is obtained through scraping method using Octoparse. A total of 1,852 tweets from 1/1/2019 to 15/10/2019 were divided into 1,130 tweet testing data and 722 tweet training data. Then, RapidMiner was used for analysis process. Analysis positive sentiment using SVM is 62% and negative sentiment is 38%, while in SVM-PSO, positive opinion is 53% and negative opinion is 47%. The results of research using 10 k-fold CV produce accuracy on SVM is 95.46% and AUC is 0.979 (excellent classification), while in SVM-PSO accuracy is 96.04% and AUC is 0.993 (excellent classification). The results show that use of training and testing data on this study can be done and prove that SVM-PSO is better than ordinary SVM, although the parameters value is default.
References
T. Abadi (2018) Catatan Perlindungan Konsumen 2018 (edisi 1): Ekonomi Digital dan Marginalisasi Hak Konsumen, [Online], https://ylki.or.id/2018/12/catatan-perlindungan-konsumen-2018-edisi-1-ekonomi-digital-dan-marginalisasi-hak-konsumen/, tanggal akses: 20-Okt-2019.
P. Arhando (2019) Jika Tarif Ojek Online Naik, 71 Persen Konsumen Kembali Gunakan Kendaraan Pribadi, [Online], https://www.moneysmart.id/kenaikan-tarif-ojek-online-membuat-konsumer-terancam-beralih/, tanggal akses: 20-Okt-2019.
A. Pradyant, (2017) Melihat Transportasi Umum Online dan Konvensional dari Kedua Sisi, [Online], https://www.kompasiana.com/tetikusliterasi/5a082942a4b06842cf3fe392/melihat-transportasi-umum-online-dan-konvensional-dari-kedua-sisi?page=all, tanggal akses: 20-Okt-2019.
(2015) Indonesia: number of Twitter users 2014-2019. [Online], https://www.statista.com/statistics/490548/twitter-users-indonesia/, tanggal akses: 20-Okt-2019.
M. Kanakaraj dan R.M.R. Guddeti, “Performance Analysis of Ensemble Methods on Twitter Sentiment Analysis Using NLP Techniques,” Proc. 2015 IEEE 9th Int. Conf. Semantic Computing, 2015, hal. 169-170.
P.K. Gajakosh, T. Ghorpade, dan R. Shedge, “Opinion Mining for Multi-Mix Languages Hotel Review by using Fuzzy Sets,” Proc. of Int. Conf. on Advances in Science and Technology (ICAST), 2015, hal. 1-4.
E. Indrayuni, “Analisa Sentimen Review Hotel Menggunakan Algoritma Support Vector Machine Berbasis Particle Swarm Optimization,” Jurnal Evolusi, Vol. 4, No.2, hal. 20-27, 2016.
H. Tuhuteru dan A. Iriani, “Analisis Sentimen Perusahaan Listrik Negara Cabang Ambon Menggunakan Metode Support Vector Machine dan Naive Bayes Classifier,” Jurnal Pengembangan IT, Vol. 3, No. 3, hal. 394-401, 2018.
O. Somantri dan C. Supriyanto, “Algoritme Genetika untuk Peningkatan Prediksi Kebutuhan Permintaan Energi Listrik,” Jurnal Nasional Teknik Elektro dan Teknologi Informasi, Vol. 5, No. 2, hal. 108-114, 2016.
B. Liu, Sentiment Analysis and Opinon Mining, California, USA: Morgan & Claypool Publishers, 2012.
A. D’Andrea, F. Ferri, P. Grifoni, dan T. Guzzo, “Approaches, Tools and Applications for Sentiment Analysis Implementation,” International Journal of Computer Applications, Vol. 125, No. 3, hal. 26-33, 2015.
S.B. Bhonde dan J.R. Prasad, “Sentiment Analysis - Methods, Applications and Challenges,” International Journal of Electronics Communication and Computer Engineering, Vol. 6, No. 6, hal. 634-640, 2015.
M. Fernández-Gavilanes, T. Álvarez-López, J. Juncal-Martínez, E. Costa-Montenegro, dan F.J. González-Castaño, “Unsupervised Method for Sentiment Analysis in Online Texts,” Expert Systems with Applications, Vol. 58, hal. 57-75, 2016.
I. Zulfa dan E. Winarko, “Sentimen Analisis Tweet Berbahasa Indonesia dengan Deep Belief Network,” Indonesian Journal of Computing and Cybernetics Systems, Vol. 11, No. 2, hal. 187-198, 2017.
Z.H. Deng, K.H. Luo, dan H.L. Yu, “A Study of Supervised Term Weighting Scheme for Sentiment Analysis,” Expert Systems with Applications, Vol. 42, No. 7, hal. 3506-3513, 2014.
M. Lan, C.L. Tan, J. Su, dan Y. Lu, “Supervised and Traditional Term Weighting Methods for Automatic Text Categorization,” Pattern Analysis and Machine Intelligence, Vol. 31, No. 4, hal. 721-735, 2009.
B. Santosa, “Tutorial Support Vector Machine,” Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia, Tutorial, hal. 1-19, 2015.
R. Feldman dan J. Sanger, The Text Mining Handbook, New York, USA: Cambridge University Press, 2007.
W. He, S. Zha, dan L. Li, “Social Media Competitive Analysis and Text Mining: A Case Study in the Pizza Industry,” International Journal of Information Management, Vol. 33, No.3, hal. 464-472, 2013.
N. Yunita, “Analisis Sentimen Berita Artis dengan Menggunakan Algoritma Support Vector Machine dan Particle Swarm Optimization,” Jurnal Sistem Informasi, Vol. 5, No. 2, hal. 104-112, 2017.
S.S. Istia dan H.D. Purnomo, “Sentiment Analysis of Law Enforcement Performance Using Support Vector Machine dan K-Nearest Neighbor,” 3rd International Conference on Information Technology, Information System and Electrical Engineering (ICITISEE), 2018, hal. 84-89.
T.B. Sasongko, “Komparasi dan Analisis Kinerja Model Algoritma SVM dan PSO-SVM (Studi Kasus Klasifikasi Jalur Minat SMA),” Jurnal Teknik Informatika dan Sistem Informasi, Vol. 2, No. 2, hal. 244-253, 2016.
F. Gorunescu, Data Mining: Concepts, Models and Techniques, Berlin: Germany: Springer-Verlag Berlin Heidelberg, 2011.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
