Sentiment Analysis of Public Opinion on the 2024 Presidential Election in Indonesia Using Twitter Data with the K-NN Method
Digitus : Journal of Computer Science Applications · 2023
DOI: 10.61978/digitus.v1i1.27 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digitus : Journal of Computer Science Applications, 2023. Verfasst von Karno Diantoro und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Twitter is often used by the public as a platform to speak and express their opinions, especially in the context of the 2024 Presidential Election. Tweets related to the '2024 Presidential Election' can be used as a source of data for social media analysis to determine whether the expressed opinions tend to be positive or negative. The research process involves data collection of tweets, preprocessing, tokenization, class attribute determination, directory filling, sentiment analysis, and classification steps, including testing the value of k and testing the confusion matrix. The research and testing results show that the K-NN method successfully achieves a sentiment classification accuracy rate of 86.48%.
Zitieren
APA
Diantoro, K., Soderi, A., Rohman, A., & Sitorus, A. T. (2023). Sentiment Analysis of Public Opinion on the 2024 Presidential Election in Indonesia Using Twitter Data with the K-NN Method. Digitus : Journal of Computer Science Applications. https://doi.org/10.61978/digitus.v1i1.27
Vancouver
Diantoro K, Soderi A, Rohman A, Sitorus AT. Sentiment Analysis of Public Opinion on the 2024 Presidential Election in Indonesia Using Twitter Data with the K-NN Method. Digitus : Journal of Computer Science Applications. 2023. doi:10.61978/digitus.v1i1.27
BibTeX
@article{Diantoro2023,
author = {Diantoro, Karno and Soderi, Ahmad and Rohman, Abdur and Sitorus, Anwar T.},
title = {Sentiment Analysis of Public Opinion on the 2024 Presidential Election in Indonesia Using Twitter Data with the K-NN Method},
journal = {Digitus : Journal of Computer Science Applications},
year = {2023},
doi = {10.61978/digitus.v1i1.27}
}
EUVIMED