Perbandingan Algoritma Machine Learning Dan Deep Learning Untuk Analisis Sentimen Beasiswa LPDP

Dewi, Adinda Risky and , Dr. Eng. Yusuf Sulistyo Nugroho, M.Eng. (2026) Perbandingan Algoritma Machine Learning Dan Deep Learning Untuk Analisis Sentimen Beasiswa LPDP. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) publikasi_fix.pdf Download (612kB)
	PDF (Surat Pernyataan Publikasi) Surat pernyataan publikasi_Adinda.pdf Restricted to Repository staff only Download (1MB)

Abstract

The LPDP Scholarship (Education Fund Management Institution) is one of the Indonesian government’s major educational funding programs that has received extensive public attention, particularly through social media platforms such as Twitter (X). Public discussions on X reveal diverse responses toward this program. However, public perception of the LPDP Scholarship has not yet been clearly identified, even though it can serve as an important basis for program evaluation and improvement. Therefore, this study conducts a public sentiment analysis of the LPDP Scholarship program. The analysis compares the performance Machine Learning and Deep Learning of four text classification methods, namely Multinomial Naïve Bayes and Support Vector Machine (SVM) for Machine Learning, Long Short-Term Memory (LSTM), and IndoBERT for Deep Learning, while also evaluating the impact of preprocessing quality on model performance. The data were collected through web scraping from X and processed through several stages, including data splitting, modeling, and evaluation. The results show that preprocessing quality has a significant impact on model performance, where the combination of manual and IndoBERT achieved the highest accuracy of 75%, followed by LSTM at 73%, SVM at 73%, and Naïve Bayes at 71%. These findings indicate that effective text processing plays a crucial role in improving the performance of Indonesian- language sentiment analysis systems

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Sentiment Analysis, LPDP Scholarship, Deep Learning, Machine Learning, Twitter
Subjects:	T Technology > Technical Information T Technology > Technical Information > Software. Aplication T Technology > Technical Information > Software. Aplication > Software Engineering
Divisions:	Fakultas Komunikasi dan Informatika > S1 Teknik Informatika
Depositing User:	ADINDA RISKY DEWI
Date Deposited:	21 Feb 2026 02:39
Last Modified:	21 Feb 2026 02:39
URI:	http://eprints.ums.ac.id/id/eprint/142935

Actions (login required)

View Item