Klasifikasi Emosi pada Teks Bahasa Indonesia dan Emoji menggunakan Algoritma Hybrid CNN-BiLSTM

Widiasmara, Rangga (2025) Klasifikasi Emosi pada Teks Bahasa Indonesia dan Emoji menggunakan Algoritma Hybrid CNN-BiLSTM. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) Cover.pdf Download (1MB)
	Text (Bab 1) Bab 1.pdf Download (4MB)
	Text (Bab 2) Bab 2.pdf Restricted to Repository staff only until 25 July 2027. Download (528kB)
	Text (Bab 3) Bab 3.pdf Restricted to Repository staff only until 25 July 2027. Download (4MB)
	Text (Bab 4) Bab 4.pdf Restricted to Repository staff only until 25 July 2027. Download (4MB)
	Text (Bab 5) Bab 5.pdf Download (257kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf Download (285kB)
	Text (Lampiran) Lampiran.pdf Restricted to Repository staff only Download (4MB)

Abstract

This research designs and comparatively evaluates four deep learning model architectures to address the challenges of emotion classification in complex and ambiguous Indonesian text and emoji. By comparing hybrid approaches (serial vs. parallel) of Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) as well as input schemes (single vs. dual) on the Emotion Twitter dataset from IndoNLU, this study finds that explicitly processing emoji features through a dual-input scheme significantly improves performance. The best model, a parallel hybrid architecture with dual inputs, successfully achieved a test accuracy of 90.16% and a Macro F1-Score of 0.90. This model proved effective in handling ambiguous classes like 'fear' and 'sadness', although a persistent challenge remains in distinguishing between 'happy' and 'sadness' classes due to linguistic complexities. These results conclude that the hybrid CNN-BiLSTM approach with a parallel and multi-input architecture is a highly effective and promising method for emotion analysis in Indonesian digital content.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	DIYASA, I GEDE SUSRAMA MAS	NIDN0019067008	igsusrama.if@upnjatim.ac.id
Thesis advisor	PUTRA, CHRYSTIA AJI	NIDN0008108605	ajiputra@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Rangga Widiasmara

Date Deposited:

25 Jul 2025 08:37

Last Modified:

25 Jul 2025 08:37

URI:

https://repository.upnjatim.ac.id/id/eprint/41094