Text

KLASIFIKASI EMOSI PADA TEKS BERBAHASA INDONESIA DENGAN FINE-TUNING INDOBERT

---

Penilaian

---

The increasing use of social media has led to significant growth in Indonesian text data, creating complexity in emotion identification and classification tasks. To address this challenge, this study develops an emotion classification system using the fine-tuning method on the IndoBERT model. This research aims to classify emotions in Indonesian text using IndoBERT fine-tuning. The study utilizes two types of datasets: an imbalanced dataset comprising 4,403 tweets sourced from IndoNLU and a balanced dataset containing 5,600 tweets combined from IndoNLU and Riccosan et al. (2022). The fine-tuning process is divided into eight scenarios, combining different dataset types, batch sizes, and learning rates. The results demonstrate that the fine-tuned IndoBERT model achieves optimal performance on the balanced dataset with 78.55% accuracy, 78,55% recall, 78,64% precision and 78.46% f1-score using a learning rate of 4e-6 and batch size of 32. For the imbalanced dataset, the model attains 75% accuracy, 75,26% recall, 75,60% precision and 75.46% f1-score with a learning rate of 4e-6 and batch size of 16.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507001923	T169992	T1699922025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1699922025

Publisher

: Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvi, 136 hlm.; ill.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

EM

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment