Penerapan long short-term memory dan TF-IDF dalam mengklasifikasikan sentimen publik terhadap kebijakan efisiensi anggaran 2025

Maharani, Hamidah Lutfiyanti, Hariyadi, M. Amin ORCID: https://orcid.org/0000-0001-9327-7604 and Abidin, Zainal ORCID: https://orcid.org/0000-0002-9261-4952 (2026) Penerapan long short-term memory dan TF-IDF dalam mengklasifikasikan sentimen publik terhadap kebijakan efisiensi anggaran 2025. JURNAL TEKNOLOGI INFORMASI: Teori, Konsep dan Implementasi, 16 (2). pp. 77-85. ISSN 2712-1975

Preview

Text 28037.pdf - Published Version Available under License Creative Commons Attribution. Download (387kB) | Preview

Abstract

The 2025 Budget Efficiency Policy has generated diverse public responses, widely expressed through social media, making sentiment analysis necessary to understand overall public opinion. The main problem addressed in this study is how to accurately classify public sentiment toward the policy using unstructured text data. This research aims to classify public sentiment into positive and negative categories and to evaluate the performance of the Long Short-Term Memory (LSTM) model combined with Term Frequency–Inverse Document Frequency (TF-IDF). The research method involves collecting 2,222 tweets from the X platform, manual data labeling, text preprocessing, TFIDF weighting, and sentiment classification using the LSTM model. Model performance is evaluated using accuracy, precision, recall, and F1-score across several data-splitting scenarios. The results show that the combination of LSTM and TF-IDF performs effectively in sentiment classification. The best performance is achieved with an 80:20 data split, 10 epochs, and a batch size of 32, resulting in an accuracy of 94.38%, precision of 93.75%, recall of 89.44%, and F1-score of 91.55%. These findings indicate that LSTM is well suited for analyzing public sentiment toward government policies based on social media data

Item Type:	Journal Article
Keywords:	efisiensi anggaran2025; klasifikasi sentimen; lstm; tf-idf
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080105 Expert Systems
Divisions:	Graduate Schools > Magister Programme > Graduate School of Informatics Engineering
Depositing User:	Mokhamad Amin Hariyadi
Date Deposited:	13 Jul 2026 11:32

Downloads

Origin of downloads

Actions (login required)

View Item