TY - GEN
T1 - Analyzing Public Sentiment on Electric Vehicles in Indonesia
T2 - 7th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2024
AU - Wibowo, Agus Hindarto
AU - Wirjodirdjo, Budisantoso
AU - Singgih, Moses Laksono
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - This study examines public sentiment toward electric vehicles (EVs) in Indonesia through an analysis of social media data from platform X. The results reveal that the overall sentiment is predominantly negative, with 53% of the 185 tweets expressing negative opinions, while 47% conveyed positive sentiments. This indicates that, while there is significant enthusiasm for EVs among a portion of the population, many remain skeptical about the technology, particularly regarding policies and vehicle performance. Additionally, text mining and sentiment analysis identified key topics driving public concern, with terms such as "tax,""motor,""Indonesia,""battery,"and "subsidy"frequently mentioned. These terms reflect the primary areas of discussion contributing to the public's uncertainty about EV adoption. In terms of sentiment classification methods, Support Vector Machine (SVM) was the most accurate, achieving an accuracy of 74.68%, outperforming Naive Bayes, Random Forest (62.93%), and Gradient Booster (59.49%). These findings that further research is necessary to explore the factors influencing public perception and to develop strategies for improving EV adoption in Indonesia.
AB - This study examines public sentiment toward electric vehicles (EVs) in Indonesia through an analysis of social media data from platform X. The results reveal that the overall sentiment is predominantly negative, with 53% of the 185 tweets expressing negative opinions, while 47% conveyed positive sentiments. This indicates that, while there is significant enthusiasm for EVs among a portion of the population, many remain skeptical about the technology, particularly regarding policies and vehicle performance. Additionally, text mining and sentiment analysis identified key topics driving public concern, with terms such as "tax,""motor,""Indonesia,""battery,"and "subsidy"frequently mentioned. These terms reflect the primary areas of discussion contributing to the public's uncertainty about EV adoption. In terms of sentiment classification methods, Support Vector Machine (SVM) was the most accurate, achieving an accuracy of 74.68%, outperforming Naive Bayes, Random Forest (62.93%), and Gradient Booster (59.49%). These findings that further research is necessary to explore the factors influencing public perception and to develop strategies for improving EV adoption in Indonesia.
KW - Classification model
KW - Data mining
KW - Electric Vehicles
KW - Sentiment Analysis
KW - Text Mining
UR - https://www.scopus.com/pages/publications/105004417112
U2 - 10.1109/ISRITI64779.2024.10963484
DO - 10.1109/ISRITI64779.2024.10963484
M3 - Conference contribution
AN - SCOPUS:105004417112
T3 - 7th International Seminar on Research of Information Technology and Intelligent Systems: Advanced Intelligent Systems in Contemporary Society, ISRITI 2024 - Proceedings
SP - 409
EP - 414
BT - 7th International Seminar on Research of Information Technology and Intelligent Systems
A2 - Wibowo, Ferry Wahyu
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 December 2024
ER -