Latifah, Retnani and Baddalwan, Ridwan and Saputra, Ambar Dwi and Meilina, Popy and Adharani, Yana (2021) Sentiment Analysis of COVID-19 Vaccines from Indonesian Tweets and News Headlines. In: The 2021 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

Text (Sentiment Analysis of COVID-19 Vaccines from Indonesian Tweets and News Headlines) Paper ICACSIS.pdf - Submitted Version Download (763kB)

Abstract

COVID-19 vaccines is a hot topic in online platforms due to the ongoing pandemic. Most studies on sentiment analysis of COVID-19 vaccines on Indonesian social media posts only used one or two classifiers with few modifications. This research investigated sentiment analysis using seven machine learning techniques on Twitter dataset which then used to predict on other unlabeled Twitter datasets as well as news headlines dataset. The experiment revealed that using the unigram bag-of-word KNN method gave the best result with 80.6% accuracy and slight overfit, 2.9% difference between training and testing accuracy. This classifier managed to capture a similar pattern of sentiment in Twitter datasets, which is dominated by neutral sentiment. In addition, the classifier could be used to classify different dataset, such as news headlines, with accuracy of 70% and could capture important words in negative sentiment.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions:	Faculty of Engineering / Fakultas Teknik > S1 Informatics Engineering / Teknik Informatika
Depositing User:	Yana Adharani
Date Deposited:	31 Aug 2021 01:29
Last Modified:	31 Aug 2021 01:29
URI:	http://repository.umj.ac.id/id/eprint/6352

Actions (login required)

View Item