Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Fine-Grained Sentiment Classification of Public Opinion on Electric Cars in Indonesia Using IndoBERT

Rektorat UDINUS 2024 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2024
Goals
Record
762944ef-806e-4948-9217-c4abf977ae6a
Published
2026-10-30

Universitas Dian Nuswantoro conducted research to analyze public sentiment towards electric cars in Indonesia using the IndoBERT model. The activity involved UDINUS researchers Alamsyah, Nur; Noersasongko, Edi; Shidik, Guruh Fajar; and Rijati, Nova. The research examined Indonesian-language public opinion collected from social media platforms, especially Twitter or X. Its stated aim was to analyze public sentiment towards electric cars in Indonesia through the IndoBERT model.

The dataset consisted of 1,087 tweets. The tweets were preprocessed and labelled into five sentiment categories: very positive, positive, neutral, negative, and very negative. According to the study's findings, the majority of public opinion in Indonesia was neutral, representing 70.45%. Positive opinion represented 21.65%, negative opinion represented 6.13%, very positive opinion represented 1.49%, and very negative opinion represented 0.28%. The study also stated that the overall trend was positive. At the same time, the findings identified concerns about charging infrastructure and the price of electric cars.

UDINUS processed the dataset using the IndoBERT model for Indonesian-language public opinion. The enhanced IndoBERT model achieved an accuracy increase from 74% in the first epoch to 80% in the fifth epoch. Its F1 score increased from 0.83 to 0.89. These results describe the reported performance of the model in classifying public opinion into the five stated sentiment categories.

The research provided insights for policymakers and manufacturers in supporting the adoption of electric cars in Indonesia. In relation to the supplied goal, the activity documents research on electric cars, Indonesian public opinion, charging infrastructure concerns, price concerns, and the application of IndoBERT for sentiment classification. The activity therefore presents a documented institutional research effort by Universitas Dian Nuswantoro based on the stated dataset, method, categories, findings, and model performance.

Reference https://www.scopus.com/pages/publications/85213305455?origin=resultslist