Skripsi

ANALISIS SENTIMEN MASYARAKAT TERHADAP AWAL KEPEMIMPINAN PRESIDEN PRABOWO SUBIANTO MENGGUNAKAN METODE INDOBERT

---

This research aims to analyze public sentiment toward the early leadership of President Prabowo Subianto using the IndoBERT language model. Public opinions were collected from various social media platforms, including X, YouTube and TikTok, resulting in a dataset of 78,851 texts labeled into positive and negative sentiments. The data underwent preprocessing stages such as cleaning, case folding, normalization, tokenization, and embedding before being used to fine-tune the IndoBERT model. Three different training scenarios were implemented to identify the most optimal configuration for sentiment classification. The evaluation results show that the second scenario using 3 epochs, batch size 128, learning rate 2e-5, and AdamW optimizer achieved the best performance with an accuracy of 93.5% and balanced precision, recall, and F1-score. These findings indicate that IndoBERT is highly effective in analyzing Indonesian political sentiment and can be applied in broader public opinion monitoring tasks.

---

Availability

Detail Information

Series Title

-

Call Number

T1950812026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xi, VI-2 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Pembelajaran Mesin

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment