Pendekatan Text Mining dalam Menilai Sentimen Publik pada Baterai Kendaraan Listrik
Keywords:
Text Mining, Analisis Sentimen, Word Cloud, LDA, Baterai Kendaraan ListrikAbstract
The use of technology and information in the Industry 4.0 era has been widely used to extract information from textual data patterns. The development of technology and the availability of big data from various platforms can provide valuable insights and facilitate better decision making. In this study, we aim to extract information and obtain the main topics of public sentiment on electric vehicle batteries. The data source is obtained from the results of comments or tweets on X social media. A total of 1,302 texts were processed using text mining techniques in the orange data mining application. This technique consists of several stages of text processing, namely transformation, filtering and tokenisation. The results of the text processing are extracted by word cloud to find the characteristics of words that are often discussed by the community. Next, sentiment analysis is performed to find out people's opinions about electric vehicle batteries based on positive, negative and neutral categories. Finally, topic modelling is performed using LDA to identify the topics discussed in each sentiment category. The results showed that public opinion was divided into three categories: 37% positive, 42% neutral and 21% negative. A frequently discussed topic in relation to electric vehicle batteries is the word feature nickel. Topic modelling produces five main topic categories that are frequently discussed by the public.
References
[1] A. A. Visaria, A. F. Jensen, M. Thorhauge, and S. E. Mabit, “User preferences for EV charging, pricing schemes, and charging infrastructure,” Transp. Res. Part A Policy Pract., vol. 165, no. September, pp. 120–143, 2022, doi: 10.1016/j.tra.2022.08.013.
[2] I. Mahmud, M. B. Medha, and M. Hasanuzzaman, “Global challenges of electric vehicle charging systems and its future prospects: A review,” Res. Transp. Bus. Manag., vol. 49, no. June, p. 101011, 2023, doi: 10.1016/j.rtbm.2023.101011.
[3] M. I. Alhari, O. N. Pratiwi, and M. Lubis, “Sentiment Analysis of The Public Perspective Electric Cars in Indonesia Using Support Vector Machine Algorithm,” 2022 Int. Conf. Sci. Inf. Technol. Smart Adm. ICSINTESA 2022, pp. 155–160, 2022, doi: 10.1109/ICSINTESA56431.2022.10041604.
[4] V. Singh, V. Singh, and S. Vaibhav, “A review and simple meta-analysis of factors influencing adoption of electric vehicles,” Transp. Res. Part D Transp. Environ., vol. 86, no. August, p. 102436, 2020, doi: 10.1016/j.trd.2020.102436.
[5] A. Pamidimukkala, S. Kermanshachi, J. M. Rosenberger, and G. Hladik, “Barriers and motivators to the adoption of electric vehicles: A global review,” Green Energy Intell. Transp., vol. 3, no. 2, p. 100153, 2024, doi: 10.1016/j.geits.2024.100153.
[6] B. Gong, R. Liu, X. Zhang, C. Ter Chang, and Z. Liu, “Sentiment analysis of online reviews for electric vehicles using the SMAA-2 method and interval type-2 fuzzy sets,” Appl. Soft Comput., vol. 147, p. 110745, 2023, doi: 10.1016/j.asoc.2023.110745.
[7] G. Y. Pratomo, “Penetrasi Kendaraan Listrik Masih Kecil, Saham Ini Jadi Pilihan Menarik,” https://www.liputan6.com/saham/read/5407508/penetrasi-kendaraan-listrik-masih-kecil-saham-ini-jadi-pilihan-menarik, 2023. https://www.liputan6.com/saham/read/5407508/penetrasi-kendaraan-listrik-masih-kecil-saham-ini-jadi-pilihan-menarik.
[8] R. Jena, “An empirical case study on Indian consumers’ sentiment towards electric vehicles: A big data analytics approach,” Ind. Mark. Manag., vol. 90, no. November 2018, pp. 605–616, 2020, doi: 10.1016/j.indmarman.2019.12.012.
[9] J. Axsen, C. Orlebar, and S. Skippon, “Social influence and consumer preference formation for pro-environmental technology: The case of a U.K. workplace electric-vehicle study,” Ecol. Econ., vol. 95, pp. 96–107, 2013, doi: 10.1016/j.ecolecon.2013.08.009.
[10] Q. Qin, Z. Zhou, J. Zhou, Z. Huang, X. Zeng, and B. Fan, “Sentiment and attention of the Chinese public toward electric vehicles: A big data analytics approach,” Eng. Appl. Artif. Intell., vol. 127, no. PA, p. 107216, 2024, doi: 10.1016/j.engappai.2023.107216.
[11] M. Wang, H. You, H. Ma, X. Sun, and Z. Wang, “Sentiment Analysis of Online New Energy Vehicle Reviews,” Appl. Sci., vol. 13, no. 14, 2023, doi: 10.3390/app13148176.
[12] B. Gong, R. Liu, and X. Zhang, “Market acceptability assessment of electric vehicles based on an improved stochastic multicriteria acceptability analysis-evidential reasoning approach,” J. Clean. Prod., vol. 269, p. 121990, 2020, doi: 10.1016/j.jclepro.2020.121990.
[13] S. Kumar and S. Gawade, “Sentiment Analysis of opinions about Electric Vehicles Using Twitter data,” 2023 IEEE 7th Conf. Inf. Commun. Technol. CICT 2023, pp. 1–5, 2023, doi: 10.1109/CICT59886.2023.10455654.
[14] Z. Wu, Q. He, J. Li, G. Bi, and M. F. Antwi-Afari, “Public attitudes and sentiments towards new energy vehicles in China: A text mining approach,” Renew. Sustain. Energy Rev., vol. 178, no. March, p. 113242, 2023, doi: 10.1016/j.rser.2023.113242.
[15] T. Ye, S. Zhao, C. K. M. Lau, and F. Chau, “Social media sentiment of hydrogen fuel cell vehicles in China: Evidence from artificial intelligence algorithms,” Energy Econ., vol. 133, no. April, p. 107564, 2024, doi: 10.1016/j.eneco.2024.107564.
[16] Luth, Kismartini, D. Lituhayu, R. Maswati, and T. Baharuddin, “Public Response on Twitter: The Urgency of Government Policy on Electric Vehicles,” E3S Web Conf., vol. 440, pp. 1–8, 2023, doi: 10.1051/e3sconf/202344003023.
[17] R. A. Ekatama, M. Rahardi, A. Aminuddin, and F. F. Abdulloh, “Sentiment Analysis of Electric Vehicles in Indonesia Using Support Vector Machine and Naïve Bayes,” Proc. 3rd 2023 Int. Conf. Smart Cities, Autom. Intell. Comput. Syst. ICON-SONICS 2023, no. December, pp. 120–125, 2023, doi: 10.1109/ICON-SONICS59898.2023.10435277.
[18] J. R. Batmetan and T. Hariguna, “Sentiment Unleashed: Electric Vehicle Incentives Under the Lens of Support Vector Machine and TF-IDF Analysis,” J. Appl. Data Sci., vol. 5, no. 1, pp. 122–132, 2024, doi: 10.47738/jads.v5i1.162.
[19] S. Ou, “Estimate long-term impact on battery degradation by considering electric vehicle real-world end-use factors,” J. Power Sources, vol. 573, no. April, p. 233133, 2023, doi: 10.1016/j.jpowsour.2023.233133.
[20] U. Qamar and M. S. Raja, “Text Mining Applications,” in Applied Text Mining, Springer Cham, 2024, p. 53.
[21] O. Alsemaree, A. S. Alam, S. S. Gill, and S. Uhlig, “Sentiment analysis of Arabic social media texts: A machine learning approach to deciphering customer perceptions,” Heliyon, vol. 10, no. 9, p. e27863, 2024, doi: 10.1016/j.heliyon.2024.e27863.
[22] P. K. Jayasekara and K. S. Abu, “Text Mining of Highly Cited Publications in Data Mining,” IEEE 5th Int. Symp. Emerg. Trends Technol. Libr. Inf. Serv. ETTLIS 2018, pp. 128–130, 2018, doi: 10.1109/ETTLIS.2018.8485261.
[23] Preeti, “Review on Text Mining: Techniques, Applications and Issues,” Proc. 2021 10th Int. Conf. Syst. Model. Adv. Res. Trends, SMART 2021, pp. 474–478, 2021, doi: 10.1109/SMART52563.2021.9676285.
[24] Y. Zhang, M. Chen, and L. Liu, “A review on text mining,” Proc. IEEE Int. Conf. Softw. Eng. Serv. Sci. ICSESS, vol. 2015-Novem, pp. 681–685, 2015, doi: 10.1109/ICSESS.2015.7339149.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Trisna Yuniarti, Juli Astuti, Firdhani Faujiyah, M. Zaiyar (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
