Performance Analysis of LSTM, GRU and IndoBERT Variants for Emotion Detection in Indonesian Text
Journal of Applied Informatics and Computing · 16.04.2026 · 10 (2) · 1172-1181
DOI: 10.30871/jaic.v10i2.12002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 16.04.2026. Verfasst von Putri Innayah Mahmid und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
This study evaluates gating mechanisms, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in comparison with attention-based models utilizing IndoBERT variants (Base, Large, and Lite) for Indonesian emotion detection across six emotion labels. The evaluation examines accuracy, efficiency, and robustness using both in-distribution and out-of-distribution (OOD) datasets collected from social media. Statistical significance is assessed through confidence interval estimation and bootstrap paired tests, and a detailed error analysis is conducted to identify model limitations. The results indicate that IndoBERT Large achieves superior performance, with a Macro F1-Score of 80.05% and greater robustness to domain shifts, whereas gating models exhibit substantial performance degradation on unseen data. In contrast, GRU outperforms LSTM and achieves the lowest inference latency, with training times up to 131 times faster than IndoBERT Large. Statistical tests confirm that the performance gap between IndoBERT variants and RNN-based models is significant. These findings highlight a key trade-off: attention mechanisms provide state-of-the-art accuracy and robustness, while GRU offers a practical and efficient solution for resource-constrained settings.
Zitieren
APA
Mahmid, P. I., & Lapatta, N. T. (2026). Performance Analysis of LSTM, GRU and IndoBERT Variants for Emotion Detection in Indonesian Text. Journal of Applied Informatics and Computing, 10(2), 1172-1181. https://doi.org/10.30871/jaic.v10i2.12002
Vancouver
Mahmid PI, Lapatta NT. Performance Analysis of LSTM, GRU and IndoBERT Variants for Emotion Detection in Indonesian Text. Journal of Applied Informatics and Computing. 2026;10(2):1172-1181. doi:10.30871/jaic.v10i2.12002
BibTeX
@article{Mahmid2026,
author = {Mahmid, Putri Innayah and Lapatta, Nouval Trezandy},
title = {Performance Analysis of LSTM, GRU and IndoBERT Variants for Emotion Detection in Indonesian Text},
journal = {Journal of Applied Informatics and Computing},
year = {2026},
volume = {10},
number = {2},
pages = {1172--1181},
doi = {10.30871/jaic.v10i2.12002}
}
EUVIMED