Article Per Year (5 Year)
p-Index From 2020 - 2025
3.495
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Teknik Informatika Jurnal EECCIS Jurnal Teknik Elektro dan Komputer
Agustinus Jacobus
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering Library & Information Science

Published : 38 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Jurnal EECCIS

 1 
Implementation of Feature Extraction Using BERT in Aspect Based Sentiment Analysis Turangan, Andreas Dwi Putra; Jacobus, Agustinus; Kambey, Feisy Diane
Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems) Vol. 19 No. 2 (2025)
Publisher : Faculty of Engineering, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/jeeccis.v19i2.1770

Abstract

Aspect Based Sentiment Analysis (ABSA) is a sentiment analysis technique that not only identifies overall sentiment, but also reveals opinions on specific aspects of an entity. To facilitate computer processing, a numerical representation of words into vectors (word embedding) is used, where each word or phrase is mapped into a vector of dimension N. Although static embedding such as Word2Vec or GloVe has been widely used, these approaches have limitations in capturing the dynamic context essential for deep sentiment analysis. This research develops and tests several deep learning algorithms, namely CNN, Bi-LSTM, CNN+BiLSTM, and CNN+BiLSTM+Attention Mechanism, which initially use static embedding and then modified by integrating BERT as contextual embedding. The results show that the use of BERT improves sentiment prediction accuracy by 15% and aspect prediction accuracy by 11% compared to models with static embedding. In particular, the combination of BERT+CNN obtained the best accuracy, which was 94% for aspect prediction and the combination of BERT+CNN+BiLSTM+Attention Mechanism 87% for sentiment prediction. These findings demonstrate the significant potential of BERT integration in improving ABSA performance, which can be applied in social media opinion analysis and sentiment-based recommendation systems.
Co-Authors Ahlan Ahlan Alicia Sinsuw Alow, Ophira L.M. amelia, mongan winny Antameng, Gabriella S. Ariantini, Dewa Ayu Rai Arie Lumenta Arie S.M Lumenta, Arie S.M Arinal, Azalia A. Benefit S. Narasiang Bogar, Brando Margendy Bu'ulolo, Geza Jeremia Cassey K. N. Paputungan Dirko G.S. Ruindungan Edi Winarko Hadi, Bahmid Heilbert Armando Mapaly Jacob, Virggi E. Jane I. Litouw Joane, Yudhy Lady Joshua Axel Wuisan Kambey, Feisy Diane Kambey, Gabriella Eyrene Iriani KARAME, VAIYE EFRAIM JIRE Karter D. Putung, Karter D. Kho, Erik Erlando Linda Jayanti, Linda Litouw, Jane I. Makalalag, Rayditto Manajang, Dufan Martina K. E. T. Dundu, Martina K. E. T. Monica Kumaat Monica Kumaat, Monica Oktavian A. Lantang Paputungan, Cassey K. N. Reiner Lantang Rizal Sengkey Romario Lendo Rompas, Alexander Christian Ruindungan, Dirko Ruindungan, Dirko G. S. Ruindungan, Dirko G.S. salvius paulus lengkong sambul, alwin Sary D.E. Paturusi Sherwin R. U. A. Sompie Sherwin R.U.A. Sompie Sherwin Sompie Soleman, Novianti Sompie, Sherwin Sompie, Sherwin Reinaldo Unsratdianto Aldo Sondakh, Jeremia M. Steven R. Sentinuwo Steven Ray Sentinuwo Tanjung, Yudhi Pratama Tarumingkeng, Theofilio Turangan, Andreas Dwi Putra Virginia Tulenan Vortuna, Vharadien Veronika Warongan, Tessa S. Wijaya, Febyana Wilhelmina Patty Worung, Diana T. Xaverius B. N. Najoan, Xaverius B. N. Xaverius B.N. Najoan Yaulie D.Y. Rindengan Yeremia Senduk