Analisis Sentimen Pilkada di Tengah Pandemi Covid-19 Menggunakan Convolution Neural Network (CNN)
DOI:
https://doi.org/10.52436/1.jpti.60Kata Kunci:
analisis sentimen, covid-19, cnn, deep learning, NLPAbstrak
Pemilihan kepala daerah 2020 menjadi kontroversi, sebab dilaksanakan ditengah pandemi covid-19. Komentar muncul di berbagai lini media sosial seperti twitter. Banyak masyarakat yang setuju pilkada dilanjutkan, namun banyak juga yang perpendapat untuk menunda pilkada sampai masa pandemi berakhir. Melihat perbedaan pendapat seperti ini, perlu dilakukan analisis sentimen, dengan tujuan untuk memperoleh persepsi atau gambaran umum masyarakat terhadap penyelenggaraan pilkada 2020 saat pandemi covid-19. Sebanyak 500 tweet diperoleh dengan cara crawling data dari twitter API menggunakan library tweepy, bedasarkan keyword yang telah ditentukan. Dataset yang didapat diberi label ke dalam dua kelas, negatif dan positif. Penelitian ini mengusulkan pendekatan deep learning dengan algoritma Convolution Neural Network (CNN) untuk klasifikasi, yang terbukti efektif untuk tugas Natural Language Processing (NLP) dan mampu mencapai kinerja yang baik dalam klasifikasi kalimat. Percobaan dilakukan dengan menerapkan 4-layer convolutional dan mengamati pengaruh jumlah epoch terhadap akurasi model. Variasi epoch yang digunakan adalah 50, 75, 100. Hasil dari penelitian menunjukkan bahwa, metode CNN dengan dataset pilkada ditengah pandemi mendapatkan akurasi tertinggi sebesar 90% dengan 4-layer convolutional dan 100 epoch. Didapatkan pula bahwa, semakin banyak epoch yang digunakan dalam model, akurasi cenderung meningkat.
Unduhan
Referensi
M. Rudiyanto and R. Kasanova, “Dampak Covid-19 Terhadap Implementasi Pendidikan Karakter Impact of Covid-19 on The Implementation of Character Education,” Jurmal Pendidikan dan Teknologi Indonesia (JPTI)., vol. 1, no. 5, pp. 209–213, 2021, doi: https://doi.org/10.52436/1.jpti.43.
S. C. Rizki and Y. A. Hilman, “Menakar Perbedaan Opini Dalam Agenda Pelaksanaan Kontestasi Pilkada Serentak Di Tengah Covid-19,” J. Ilm. Muqoddimah, vol. 4, no. 2, pp. 143–155, 2020, doi: http://dx.doi.org/10.31604/jim.v4i2.2020.143-155.
L. Zhang, S. Wang, and B. Liu, “Deep learning for sentiment analysis: A survey,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., 2018, vol. 8, no. 4, pp. 1–25, doi: 10.1002/widm.1253.
A. U. Rehman, A. K. Malik, B. Raza, and W. Ali, “A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis,” Multimed. Tools Appl., vol. 78, no. 18, pp. 26597–26613, 2019, doi: 10.1007/s11042-019-07788-7.
D. W. Otter, J. R. Medina, and J. K. Kalita, “A Survey of the Usages of Deep Learning for Natural Language Processing,” IEEE Trans. Neural Networks Learn. Syst., vol. 32, no. 2, pp. 604–624, 2021, doi: 10.1109/TNNLS.2020.2979670.
A. Rajput, “Natural Language Processing , Sentiment Analysis and Clinical Analytics,” 2019, https://www.researchgate.net/publication/330871275_Natural_Language_Processing_Sentiment_Analysis_and_Clinical_Analytics/citations, (accessed Apr. 10, 2021)
H. Cui, Y. Lin, and T. Utsuro, “Sentiment Analysis of Tweets by CNN utilizing Tweets with Emoji as Training Data,” Proceedings of KDD (Wisdom'18), 2018, no. 4,pp. 1–8.
Z. Guan, L. Chen, W. Zhao, Y. Zheng, S. Tan, and D. Cai, “Weakly-supervised deep learning for customer review sentiment classification,” IJCAI Int. Jt. Conf. Artif. Intell. 2016, pp. 3719–3725.
S. Poria, E. Cambria, D. Hazarika, and P. Vij, “A deeper look into sarcastic tweets using deep convolutional neural networks,” COLING 2016 - 26th Int. Conf. Comput. Linguist. Proc. COLING 2016 Tech. Pap.,2016, pp. 1601–1612.
M. Rhanoui, M. Mikram, S. Yousfi, and S. Barzali, “A CNN-BiLSTM Model for Document-Level Sentiment Analysis,” Mach. Learn. Knowl. Extr., vol. 1, no. 3, pp. 832–847, 2019, doi: 10.3390/make1030048.
S. Sharma, “Epoch vs Batch Size vs Iterations,” 2017. https://towardsdatascience.com/epoch-vs-iterations-vs-batch-size-4dfb9c7ce9c9 (accessed Apr. 15, 2021)
D. Wang et al., “Modulation Format Recognition and OSNR Estimation Using CNN-Based Deep Learning,” IEEE Photonics Technol. Lett., vol. 29, no. 19, pp. 1667–1670, 2017, doi: 10.1109/LPT.2017.2742553.
M. Khader, A. Awajan, and G. Al-Naymat, “The impact of natural language preprocessing on big data sentiment analysis,” Int. Arab J. Inf. Technol., vol. 16, no. 3ASpecial Issue, pp. 506–513, 2019.
Z. Jianqiang and G. Xiaolin, “Deep Convolution Neural Networks for Twitter Sentiment Analysis,” IEEE Access, vol. 3536, no. c, 2017, doi: 10.1109/ACCESS.2017.2776930.
R. Rahutomo, A. Budiarto, K. Purwandari, A. S. Perbangsa, T. W. Cenggoro, and B. Pardamean, “Ten-year compilation of #savekpk twitter dataset,” Proc. 2020 Int. Conf. Inf. Manag. Technol. ICIMTech 2020, pp. 185–190, doi: 10.1109/ICIMTech50083.2020.9211246.
S. Alam and N. Yao, “The impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis,” Comput. Math. Organ. Theory, vol. 25, no. 3, pp. 319–335, 2019, doi: 10.1007/s10588-018-9266-8.
D. A. N. Taradhita and I. K. G. D. Putra, “Hate speech classification in Indonesian language tweets by using convolutional neural network,” J. ICT Res. Appl., vol. 14, no. 3, pp. 225–239, 2021, doi: 10.5614/itbj.ict.res.appl.2021.14.3.2.
W. Y. Chong, B. Selvaretnam, and L. K. Soon, “Natural Language Processing for Sentiment Analysis: An Exploratory Analysis on Tweets,” Proc. - 2014 4th Int. Conf. Artif. Intell. with Appl. Eng. Technol. ICAIET 2014, pp. 212–217, 2014, doi: 10.1109/ICAIET.2014.43.
M. K. Sohrabi and F. Hemmatian, “An efficient preprocessing method for supervised sentiment analysis by converting sentences to numerical vectors: a twitter case study,” Multimed. Tools Appl., 2019, doi: 10.1007/s11042-019-7586-4.
A. Bayhaqy, S. Sfenrianto, K. Nainggolan, and E. R. Kaburuan, “Sentiment Analysis about E-Commerce from Tweets Using Decision Tree, K-Nearest Neighbor, and Naïve Bayes,” 2018 Int. Conf. Orange Technol. ICOT, 2018, pp. 1–6, doi: 10.1109/ICOT.2018.8705796.
S. Anastasia and I. Budi, “Twitter sentiment analysis of online transportation service providers,” 2016 Int. Conference Adv. Comput. Sci. Inf. Syst. ICACSIS, 2016, pp. 359–365.
T. B. Rohman, D. D. Purwanto, and J. Santoso, “Sentiment Analysis Terhadap Review Rumah Makan di Surabaya Memanfaatkan Algoritma Random Forest,” Prosiding Seminar Nasional Teknologi Informasi & Aplikasinya, 2018, pp. 7–11.
L. xia Luo, “Network text sentiment analysis method combining LDA text representation and GRU-CNN,” Pers. Ubiquitous Comput., vol. 23, no. 3–4, pp. 405–412, 2019, doi: 10.1007/s00779-018-1183-9.
A. Pambudi and S. Suprapto, “Effect of Sentence Length in Sentiment Analysis Using Support Vector Machine and Convolutional Neural Network Method,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 15, no. 1, p. 21, 2021, doi: 10.22146/ijccs.61627.
J. Chen, S. Yan, and K. C. Wong, “Verbal aggression detection on Twitter comments: convolutional neural network for short-text sentiment analysis,” Neural Comput. Appl., vol. 32, no. 15, pp. 10809–10818, 2020, doi: 10.1007/s00521-018-3442-0.
N. Purnama, P. K. Negara, and S. Primakara, “Deteksi Masker Pencegahan Covid19 Menggunakan Convolutional Neural,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 1, no. 10, pp. 576–583, 2021.
W. Supriyanti and D. A. Anggoro, “Classification of Pandavas Figure in Shadow Puppet Images using Convolutional Neural Networks,” Khazanah Inform. J. Ilmu Komput. dan Inform., vol. 7, no. 1, 2021, doi: https://doi.org/10.23917/khif.v7i1.12484.
##submission.downloads##
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2021 Sukma Nindi Listyarini
Artikel ini berlisensi Creative Commons Attribution 4.0 International License.
