Geni, Lenggo and Yulianti, Evi and Sensuse, Dana Indra (2023) Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), 9 (3). pp. 746-757.
![[thumbnail of 20-Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models.pdf]](http://eprints.uad.ac.id/style/images/fileicons/text.png) |
Text
20-Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models.pdf Download (830kB) |
Abstract
General election is one of the crucial moments for a democratic country, e.g., Indonesia. Good election preparation can increase people's participation in the general election. In this study, we conduct a sentiment analysis of Indonesian public opinion on the upcoming 2024 election using Twitter data and IndoBERT model. This study is aimed at helping the government and related institutions to understand public perception. Therefore, they could obtain valuable insights to better prepare for elections, including evaluating the election policies, developing campaign strategies, increasing voter engagement, addressing issues and conflicts, and increasing transparency and public trust. The main contribution of this study is threefold: (i) the application of state-of-the-art transformer-based model IndoBERT for sentiment analysis on political domain; (ii) the empirical evaluation of IndoBERT model against machine learning and lexicon-based models; and (iii) the new dataset creation for sentiment analysis in political domain. Our Twitter data shows that Indonesian public mostly reacts neutrally (83.7%) towards the upcoming 2024 election. Then, the experimental results demonstrate that IndoBERT large-p1 is the best-performing model that achieves an accuracy of 83.5%. It improves our baseline systems by 48.5% and 46.49% for TextBlob, 2.5% and 14.49% for Multinomial Naïve Bayes, and 3.5% and 13.49% for Support Vector Machine in terms of accuracy and F-1 score, respectively.
| Item Type: | Artikel Umum |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisi / Prodi: | Faculty of Industrial Technology (Fakultas Teknologi Industri) > S1-Electrical Engineering (S1-Teknik Elektro) |
| Depositing User: | M.Eng. Alfian Ma'arif |
| Date Deposited: | 10 Aug 2023 01:22 |
| Last Modified: | 10 Aug 2023 01:22 |
| URI: | http://eprints.uad.ac.id/id/eprint/43887 |
Actions (login required)
 |
View Item |