Aspect-Based Sentiment Analysis of Transportation Electrification Opinions on YouTube Comment Data
DOI:
https://doi.org/10.34123/jurnalasks.v16i2.790Keywords:
Transportation Electrification, Electric Vehicles, Aspect-Based Sentiment Analysis, Machine Learning, Transfer LearningAbstract
Introduction/Main Objectives: This research aims to conduct an aspect-based sentiment analysis of transportation electrification opinions on YouTube comment data. Background Problems: It is difficult to summarize the sentiment of many YouTube user comments related to electric vehicles (EVs) based on their aspects; therefore, aspect-based sentiment analysis is needed to conduct further analysis. Novelty: This study identifies five aspects of EV and their sentiments at the same time. The aspects are usefulness, ease of use, comfort, cost, and incentive policies. One of this study’s methods is the transfer learning model. This model can be a solution to overcome the shortcomings of deep learning in classifying aspect-based sentiment classification on small datasets. Research Methods: The sentiment classification model used is a machine learning model, namely support vector machine (SVM) and transfer learning models from pre-trained IndoBERT and mBERT. Finding/Results: Based on the experimental results, transfer learning from the IndoBERT model achieved the best performance with accuracy and F1-Score of 89.17% and 52.66%, respectively. Furthermore, the best IndoBERT model was developed with input in the form of a combination of aspects and comment sentences. Experimental results show that there is an improvement in performance with accuracy and F1-Score of 90% and 60.70%, respectively.
Downloads
References
IEA, “World Outlook,” Econ. Outlook, vol. 11, no. 4, pp. 1–8, 2016, doi: 10.1111/j.1468-0319.1987.tb00425.x.
H. Turton, “Sustainable global automobile transport in the 21st century: An integrated scenario analysis,” Technol. Forecast. Soc. Change, vol. 73, no. 6, pp. 607–629, 2006, doi: 10.1016/j.techfore.2005.10.001.
A. Ajanovic, “The future of electric vehicles: Prospects and impediments,” Wiley Interdiscip. Rev. Energy Environ., vol. 4, no. 6, pp. 521–536, 2015, doi: 10.1002/wene.160.
IQAir, “Live most polluted major city ranking.” Accessed: Aug. 30, 2023. [Online]. Available: https://www.iqair.com/world-air-quality-ranking
A. Vafaei-Zadeh, T. K. Wong, H. Hanifah, A. P. Teoh, and K. Nawaser, “Modelling electric vehicle purchase intention among generation Y consumers in Malaysia,” Res. Transp. Bus. Manag., vol. 43, no. January, p. 100784, 2022, doi: 10.1016/j.rtbm.2022.100784.
US Department of Energy, “Alternative Fuels Data Center: Electric Vehicle (EV) Definition.” Accessed: Sep. 01, 2023. [Online]. Available: https://afdc.energy.gov/laws/12660
BBC, “Kendaraan listrik disebut ‘solusi palsu’ untuk perbaiki kualitas udara di Indonesia.” [Electric vehicles deemed a 'false solutions' for improving air quality in Indonesia] (in Indonesia). Accessed: Aug. 31, 2023. [Online]. Available: https://www.bbc.com/indonesia/articles/c51qrg47241o
J. Eagle, “The Most Popular Websites by Web Traffic (1993 to 2022).” Accessed: Oct. 26, 2023. [Online]. Available: https://www.visualcapitalist.com/cp/most-popular-websites-by-web-traffic/
R. Gomez, “25 YouTube Stats_ Users, Marketing, Demographics [2023] _ Sprout Social.” Accessed: Oct. 26, 2023. [Online]. Available: https://sproutsocial.com/insights/youtube-stats/
A. U. R. Khan, M. Khan, and M. B. Khan, “Naïve Multi-label Classification of YouTube Comments Using Comparative Opinion Mining,” Procedia Comput. Sci., vol. 82, no. March, pp. 57–64, 2016, doi: 10.1016/j.procs.2016.04.009.
K. M. Kavitha, A. Shetty, B. Abreo, A. D’Souza, and A. Kondana, “Analysis and classification of user comments on YouTube videos,” Procedia Comput. Sci., vol. 177, no. 2018, pp. 593–598, 2020, doi: 10.1016/j.procs.2020.10.084.
D. Jaiswal, V. Kaushal, R. Kant, and P. Kumar Singh, “Consumer adoption intention for electric vehicles: Insights and evidence from Indian sustainable transportation,” Technol. Forecast. Soc. Change, vol. 173, no. November 2020, p. 121089, 2021, doi: 10.1016/j.techfore.2021.121089.
Z. Yang, Q. Li, Y. Yan, W. L. Shang, and W. Ochieng, “Examining influence factors of Chinese electric vehicle market demand based on online reviews under moderating effect of subsidy policy,” Appl. Energy, vol. 326, no. September, p. 120019, 2022, doi: 10.1016/j.apenergy.2022.120019.
H. Mustakim and S. Priyanta, “Aspect-Based Sentiment Analysis of KAI Access Reviews Using NBC and SVM,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 16, no. 2, p. 113, 2022, doi: 10.22146/ijccs.68903.
S. Jeong, “Aspect-Level Analysis and Predictive Modeling for Electric Vehicle Based on Aspect-Based Sentiment Analysis Using Machine Learning,” 2020.
M. T. Anwar, D. Trisanto, A. Juniar, and F. A. Sase, “Aspect-based Sentiment Analysis on Car Reviews Using SpaCy Dependency Parsing and VADER,” Adv. Sustain. Sci. Eng. Technol., vol. 5, no. 1, p. 0230109, 2023, doi: 10.26877/asset.v5i1.14897.
R. Jena, “An empirical case study on Indian consumers’ sentiment towards electric vehicles: A big data analytics approach,” Ind. Mark. Manag., no. November 2018, pp. 0–1, 2020, doi: 10.1016/j.indmarman.2019.12.012.
J. Tao and X. Fang, “Toward multi-label sentiment analysis: a transfer learning based approach,” J. Big Data, vol. 7, no. 1, pp. 1–26, 2020, doi: 10.1186/s40537-019-0278-0.
N. Liu and J. Zhao, “A BERT-Based Aspect-Level Sentiment Analysis Algorithm for Cross-Domain Text,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/8726621.
G. Xu, Z. Zhang, T. Zhang, S. Yu, Y. Meng, and S. Chen, “Aspect-level sentiment classification based on attention-BiLSTM model and transfer learning,” Knowledge-Based Syst., vol. 245, p. 108586, 2022, doi: 10.1016/j.knosys.2022.108586.
S. Studer et al., “Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology,” Mach. Learn. Knowl. Extr., vol. 3, no. 2, pp. 392–413, 2021, doi: 10.3390/make3020020.
K. Krippendorff and R. Craggs, “The Reliability of Multi-Valued Coding of Data,” Commun. Methods Meas., vol. 10, no. 4, pp. 181–198, 2016, doi: 10.1080/19312458.2016.1228863.
V. N. Gudivada, D. L. Rao, and A. R. Gudivada, “Information Retrieval: Concepts, Models, and Systems,” in Handbook of Statistics, 1st ed., vol. 38, Elsevier B.V., 2018, pp. 331–401. doi: 10.1016/bs.host.2018.07.009.
B. Trstenjak, S. Mikac, and D. Donko, “KNN with TF-IDF based framework for text categorization,” Procedia Eng., vol. 69, pp. 1356–1364, 2014, doi: 10.1016/j.proeng.2014.03.129.
A. Shiri, Introduction to Modern Information Retrieval (2nd edition). Cambridge University Press, 2008. doi: 10.1108/00242530410565256.
B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” pp. 843–857, 2020, [Online]. Available: http://arxiv.org/abs/2009.05387
P. Reafeilzadeh, L. Tang, and H. Liu, “Cross Validation,” in Contemporary Interventional Ultrasonography in Urology, 2009, pp. 1–6. doi: 10.1007/978-1-84800-217-3_1.
