Analisis sentimen terhadap PERMENDIKBUD No. 30 pada media sosial Twitter menggunakan metode Naive Bayes dan LSTM

Romadhoni, Yuliana and Holle, Khadijah Fahmi Hayati ORCID: https://orcid.org/0000-0002-6991-1748 (2022) Analisis sentimen terhadap PERMENDIKBUD No. 30 pada media sosial Twitter menggunakan metode Naive Bayes dan LSTM. Jurnal Informatika: Jurnal Pengembangan IT, 7 (2). pp. 118-124. ISSN 2548-9356

Preview

Text 14824.pdf - Published Version Available under License Creative Commons Attribution. Download (405kB) | Preview

Abstract

Research on Sentiment Analysis of public responses to PERMENDIKBUD No. 30 on Twitter social media can use Machine Learning and Deep Learning models. This study uses two methods derived from the two models, namely the Naïve Bayes method and the Long Short-Term Memory method. Data collection by crawling data using the Twitter API which uses keywords in the form of "permendikbud30" and "Sexual violence on campus". contains "Negative" and "Positive" However, the dataset that has been preprocessed is reduced to 471 data. After preprocessing is done, then the weighting process is carried out using the TF-IDF method and continued with the calculation method. The results of this study indicate that the LSTM method gets a higher performance value, namely the Accuracy value of 77%, Precision of 84%, Recall of 75%, and F1-Score of 80%. Testing the Naïve Bayes method obtained results of 76% accuracy, 75% precision, 75% recall value and 75% F1-Score.

Item Type:	Journal Article
Keywords:	sentiment analysis; PERMENDIKBUD No.30; Naïve Bayes; long short-term memory
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Khadijah Fahmi Hayati Holle
Date Deposited:	09 Jun 2023 06:16

Downloads

Origin of downloads

Actions (login required)

View Item