Best Word2vec Architecture in Sentiment Classification of Fuel Price Increase Using CNN-BiLSTM

Authors

  • Livia Naura Aqilla School of computing, Telkom University Bandung, Indonesia
  • Yuliant Sibaroni School of computing, Telkom University Bandung, Indonesia
  • Sri Suryani Prasetiyowati School of computing, Telkom University Bandung, Indonesia

DOI:

10.33395/sinkron.v8i3.12639

Keywords:

CNN-BiLSTM, Hybrid deep learning, Sentiment analysis, Twitter, Word2vec

Abstract

The policy of increasing fuel prices has been carried out frequently in recent years, due to the instability of international price fluctuations. This study uses sentiment analysis to examine fuel price increases and their impact on public sentiment. Sentiment analysis is a data processing method to obtain information about an issue by recognizing and extracting emotions or opinions from existing texts. The method used is Word2vec Continuous Bag of Words (CBOW) and Skip-gram. Testing uses different vector dimensions in each architecture and uses a CNN-BiLSTM deep learning hybrid which performs better on sizable datasets for sentiment categorization. The results showed that the CBOW model with 300 vector dimensions produced the best performance with 87% accuracy, 87% recall, 89% precision and 88% F1 score.

GS Cited Analysis

Downloads

Download data is not yet available.

Author Biographies

Livia Naura Aqilla, School of computing, Telkom University Bandung, Indonesia

 

 

Yuliant Sibaroni, School of computing, Telkom University Bandung, Indonesia

 

 

Sri Suryani Prasetiyowati, School of computing, Telkom University Bandung, Indonesia

 

 

References

7th International Conference on Computing For Sustainable Global Development (INDIACom). (n.d.).

Alvi Rahmy Royyan, & Erwin Budi Setiawan. (2022). Feature Expansion Word2Vec for Sentiment Analysis of Public Policy in Twitter. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 6(1), 78–84. doi: 10.29207/resti.v6i1.3525

Asroni, A., Fitri, H., & Prasetyo, E. (2018). Penerapan Metode Clustering dengan Algoritma K-Means pada Pengelompokkan Data Calon Mahasiswa Baru di Universitas Muhammadiyah Yogyakarta (Studi Kasus: Fakultas Kedokteran dan Ilmu Kesehatan, dan Fakultas Ilmu Sosial dan Ilmu Politik). Semesta Teknika, 21(1). doi: 10.18196/st.211211

Bharal, R., & Vamsi Krishna, O. V. (n.d.). Social Media Sentiment Analysis Using CNN-BiLSTM. International Journal of Science and Research. doi: 10.21275/SR21913110537

Buntoro, G. A. (2017). Analisis Sentimen Calon Gubernur DKI Jakarta 2017 Di Twitter. In Integer Journal (Vol. 2, Issue 1). Retrieved from https://t.co/jrvaMsgBdH

Huang, Q., Chen, R., Zheng, X., & Dong, Z. (2017). Deep sentiment representation based on CNN and LSTM. Proceedings - 2017 International Conference on Green Informatics, ICGI 2017, 30–33. doi: 10.1109/ICGI.2017.45

Intan Af, D., Febbi Handayani, S., Wijayatun Pratiwi, R., Teknik Informatika, J., Harapan Bersama, P., Mataram No, J., & Lor, P. (2021). Pengaruh Parameter Word2Vec terhadap Performa Deep Learning pada Klasifikasi Sentimen. 6(3).

Jatnika, D., Bijaksana, M. A., & Suryani, A. A. (2019). Word2vec model analysis for semantic similarities in English words. Procedia Computer Science, 157, 160–167. doi: 10.1016/j.procs.2019.08.153

Jurnal Vocational Teknik Elektronika dan Informatika. (n.d.). Retrieved from http://ejournal.unp.ac.id/index.php/voteknika/index

Kurniasih, U., & Suseno, A. T. (2022). Analisis Sentimen Terhadap Bantuan Subsidi Upah (BSU) pada Kenaikan Harga Bahan Bakar Minyak (BBM). JURNAL MEDIA INFORMATIKA BUDIDARMA, 6(4), 2335. doi: 10.30865/mib.v6i4.4958

Liu, Z. xian, Zhang, D. gan, Luo, G. zhao, Lian, M., & Liu, B. (2020). A new method of emotional analysis based on CNN–BiLSTM hybrid neural network. Cluster Computing, 23(4), 2901–2913. doi: 10.1007/s10586-020-03055-9

Manipal University Jaipur. School of Computing and Information Technology, & Institute of Electrical and Electronics Engineers. (n.d.). 2019 2nd International Conference on Intelligent Communication and Computational Techniques (ICCT) : Manipal University, Jaipur, Sep. 28-29, 2019. (Hitesh MSR, Vaibhav Vedoshi, Kalki Y.J, Kamtam Suraj, & Kumari Santoshi, Eds.). Bengaluru: International Conference on Intelligent Communication and Computational Techniques (ICCT).

Mikolov, T., Chen, K., Corrado, G., & Dean, J. (n.d.). Distributed Representations of Words and Phrases and their Compositionality.

Muhammad, P. F., Kusumaningrum, R., & Wibowo, A. (2021). Sentiment Analysis Using Word2vec and Long Short-Term Memory (LSTM) for Indonesian Hotel Reviews. Procedia Computer Science, 179, 728–735. doi: 10.1016/j.procs.2021.01.061

Munawar, putri, musdad. (2020). MENINGKATKAN REKOMENDASI MENGGUNAKAN ALGORITMA PERBEDAAN TOPIK. Journal Sistem Informasi Karya Anak Bangsa , 01 nomor 02, 1–10.

Penelitian, J., Wardani, W., Ummi Arfah, S., Sojuangon Lubis, P., & Alwashliyah Medan Coresponding Author, U. (2022). All Fields of Science J-LAS Dampak kenaikan Bahan Bakar Minyak (BBM) Terhadap Inflasi dan Implikasinya Terhadap Makroekonomi di Indonesia Impact of the increase in fuel oil (BBM) on inflation and its implications for macroeconomics in Indonesia. 2(3), 63–70. Retrieved from https://j-las.lemkomindo.org/index.php/AFoSJ-LAS/index

Putri, S. K., Amalia, A., Nababan, E. B., & Sitompul, O. S. (2021). Bahasa Indonesia pre-trained word vector generation using word2vec for computer and information technology field. Journal of Physics: Conference Series, 1898(1). doi: 10.1088/1742-6596/1898/1/012007

Rosid, M. A., Fitrani, A. S., Astutik, I. R. I., Mulloh, N. I., & Gozali, H. A. (2020). Improving Text Preprocessing for Student Complaint Document Classification Using Sastrawi. IOP Conference Series: Materials Science and Engineering, 874(1). doi: 10.1088/1757-899X/874/1/012017

Shen, Q., Wang, Z., & Sun, Y. (2017). Sentiment analysis of movie reviews based on CNN-BLSTM. IFIP Advances in Information and Communication Technology, 510, 164–171. doi: 10.1007/978-3-319-68121-4_17

Wahyu Kurniawan, F., & Maharani, W. (2020). Indonesian Twitter Sentiment Analysis Using Word2Vec. In 2020 International Conference on Data Science and Its Applications (ICoDSA). Retrieved from http://ow.ly/ZbTB50yf0jH

Widayat, W. (2021). Analisis Sentimen Movie Review menggunakan Word2Vec dan metode LSTM Deep Learning. JURNAL MEDIA INFORMATIKA BUDIDARMA, 5(3), 1018. doi: 10.30865/mib.v5i3.3111

Yue, W., & Li, L. (2020a, December 14). Sentiment analysis using word2vec-cnn-bilstm classification. 2020 7th International Conference on Social Network Analysis, Management and Security, SNAMS 2020. doi: 10.1109/SNAMS52053.2020.9336549

Yue, W., & Li, L. (2020b, December 14). Sentiment analysis using word2vec-cnn-bilstm classification. 2020 7th International Conference on Social Network Analysis, Management and Security, SNAMS 2020. doi: 10.1109/SNAMS52053.2020.9336549

Downloads


Crossmark Updates

How to Cite

Aqilla, L. N., Sibaroni, Y. ., & Prasetiyowati, S. S. . (2023). Best Word2vec Architecture in Sentiment Classification of Fuel Price Increase Using CNN-BiLSTM. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 7(3), 1653-1664. https://doi.org/10.33395/sinkron.v8i3.12639

Issue

Vol. 7 No. 3 (2023): Article Research Volume 7 Issue 3, July 2023

Section

Articles

License

Copyright (c) 2023 Livia Naura Aqilla, Yuliant Sibaroni, Sri Suryani Prasetiyowati

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Crossref
Scopus
Google Scholar
Europe PMC