Word2Vec Optimization on Bi-LSTM in Electric Car Sentiment Classification

 (*)Siti Uswah Hasanah Mail (Telkom University, Bandung, Indonesia)
 Yuliant Sibaroni (Telkom University, Bandung, Indonesia)
 Sri Suryani Prasetyowati (Telkom University, Bandung, Indonesia)

(*) Corresponding Author

Submitted: December 20, 2023; Published: January 9, 2024

Abstract

The Indonesian government is actively promoting electric vehicles. This policy has generated many sentiments from the public, both positive and negative. Public sentiment can have a significant impact on the success of government policies. Therefore, it is important to understand public sentiment towards these policies. This research develops a sentiment classification model to understand public sentiment towards electric vehicles in Indonesia. Sentiment classification is the process of identifying and measuring the positive or negative sentiment in a text. This research uses a Bi-LSTM model to perform classification on a dataset of tweets related to electric vehicles. To evaluate the performance, testing was conducted through two main scenarios. In Scenario I, the focus was on finding the optimal embedding size for two Word2Vec architectures, namely CBOW and Skip-gram. Model evaluation was performed using cross-validation to gain a deeper understanding of model performance. Scenario II focused on searching for the best dropout parameters for the Bi-LSTM model. This step aimed to find the optimal configuration for the model to generate more accurate and consistent predictions in classifying tweets related to electric vehicles. The results showed that in the context of sentiment classification on tweets about electric vehicles, the combination of CBOW with an embedding size of 200 and the Bi-LSTM model with a Dropout value of 0.2 is the best choice and achieves an accuracy of 96.31%, precision of 92.57%, Recall of 98.61%, and F1-Score of 95.49%.

Keywords


Bi-LSTM; Word2Vec; Sentiment Classification; Electric Car; Tweet

Full Text:

PDF


Article Metrics

Abstract view : 124 times
PDF - 34 times

References

A. Agus Raksodewanto, MEMBANDINGKAN MOBIL LISTRIK DENGAN MOBIL KONVENSIONAL. Prosiding Technopex ITI, 2020

A. F. Riyadi, F. R. Rahman, M. A. Nofa Pratama, M. K. Khafidli, and H. Patria, Pengukuran Sentimen Sosial Terhadap Teknologi Kendaraan Listrik: Bukti Empiris di Indonesia, EXPERT: Jurnal Manajemen Sistem Informasi dan Teknologi, vol. 11, no. 2, p. 141, Dec. 2021, doi: 10.36448/expert.v11i2.2171.

A. Santoso, A. Nugroho, and A. S. Sunge, Analisis Sentimen Tentang Mobil Listrik Dengan Metode Support Vector Machine Dan Feature Selection Particle Swarm Optimization, Journal of Practical Computer Science, vol. 2, no. 1, pp. 2431, Jul. 2022, doi: 10.37366/jpcs.v2i1.1084.

Y. Pratama, D. Triantoro Murdiansyah, and K. Muslim Lhaksmana, Analisis Sentimen Kendaraan Listrik Pada Media Sosial Twitter Menggunakan Algoritma Logistic Regression dan Principal Component Analysis, 2023, doi: 10.30865/mib.v7i1.5575.

W. Widayat, Analisis Sentimen Movie Review menggunakan Word2Vec dan metode LSTM Deep Learning, JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 3, p. 1018, Jul. 2021, doi: 10.30865/mib.v5i3.3111.

A. Shrestha, H. Li, J. Le Kernec, and F. Fioranelli, Continuous Human Activity Classification from FMCW Radar with Bi-LSTM Networks, IEEE Sens J, vol. 20, no. 22, pp. 1360713619, Nov. 2020, doi: 10.1109/JSEN.2020.3006386.

M. Arbane, R. Benlamri, Y. Brik, and A. D. Alahmar, Social media-based COVID-19 sentiment classification model using Bi-LSTM, Expert Syst Appl, vol. 212, p. 118710, Feb. 2023, doi: 10.1016/j.eswa.2022.118710.

A. Purwarianti and I. A. P. A. Crisdayanti, Improving Bi-LSTM Performance for Indonesian Sentiment Analysis Using Paragraph Vector, in 2019 International Conference of Advanced Informatics: Concepts, Theory and Applications (ICAICTA), IEEE, Sep. 2019, pp. 15. doi: 10.1109/ICAICTA.2019.8904199.

B. Jang, M. Kim, G. Harerimana, S. Kang, and J. W. Kim, Bi-LSTM Model to Increase Accuracy in Text Classification: Combining Word2vec CNN and Attention Mechanism, Applied Sciences, vol. 10, no. 17, p. 5841, Aug. 2020, doi: 10.3390/app10175841.

P. F. Muhammad, R. Kusumaningrum, and A. Wibowo, Sentiment Analysis Using Word2vec And Long Short-Term Memory (LSTM) For Indonesian Hotel Reviews, Procedia Comput Sci, vol. 179, pp. 728735, 2021, doi: 10.1016/j.procs.2021.01.061.

L. N. Aqilla, Y. Sibaroni, and S. S. Prasetiyowati, Word2vec Architecture in Sentiment Classification of Fuel Price Increase Using CNN-BiLSTM Method, Sinkron, vol. 8, no. 3, pp. 16541664, Jul. 2023, doi: 10.33395/sinkron.v8i3.12639.

S. Tam, R. Ben Said, and O. O. Tanriover, A ConvBiLSTM Deep Learning Model-Based Approach for Twitter Sentiment Classification, IEEE Access, vol. 9, pp. 4128341293, 2021, doi: 10.1109/ACCESS.2021.3064830.

L. Xiao, G. Wang, and Y. Zuo, Research on Patent Text Classification Based on Word2Vec and LSTM, in 2018 11th International Symposium on Computational Intelligence and Design (ISCID), IEEE, Dec. 2018, pp. 7174. doi: 10.1109/ISCID.2018.00023.

S. Amin, M. I. Uddin, M. A. Zeb, A. A. Alarood, M. Mahmoud, and M. H. Alkinani, Detecting Dengue/Flu Infections Based on Tweets Using LSTM and Word Embedding, IEEE Access, vol. 8, pp. 189054189068, 2020, doi: 10.1109/ACCESS.2020.3031174.

R. H. Yahya, W. Maharani, and R. Wijaya, JURNAL MEDIA INFORMATIKA BUDIDARMA Disaster Management Sentiment Analysis Using the BiLSTM Method, 2023, doi: 10.30865/mib.v7i1.5573.

A. S. W. R. Yuliya Astari, Analisis Sentimen Multi-Class pada Sosial Media menggunakan metode Long Short-Term Memory (LSTM), vol. 4, pp. 15, Mar. 2021.

G. Futia, A. Vetro, A. Melandri, and J. C. De Martin, Training Neural Language Models with SPARQL queries for Semi-Automatic Semantic Mapping, Procedia Comput Sci, vol. 137, pp. 187198, 2018, doi: 10.1016/j.procs.2018.09.018.

G. Liu and J. Guo, Bidirectional LSTM with attention mechanism and convolutional layer for text classification, Neurocomputing, vol. 337, pp. 325338, Apr. 2019, doi: 10.1016/j.neucom.2019.01.078.

U. B. Mahadevaswamy and P. Swathi, Sentiment Analysis using Bidirectional LSTM Network, Procedia Comput Sci, vol. 218, pp. 4556, 2023, doi: 10.1016/j.procs.2022.12.400.

H. Gandhi and V. Attar, Extracting Aspect Terms using CRF and Bi-LSTM Models, Procedia Comput Sci, vol. 167, pp. 24862495, 2020, doi: 10.1016/j.procs.2020.03.301.

D. R. Alghifari, M. Edi, and L. Firmansyah, Implementasi Bidirectional LSTM untuk Analisis Sentimen Terhadap Layanan Grab Indonesia, Jurnal Manajemen Informatika (JAMIKA), vol. 12, no. 2, pp. 8999, Sep. 2022, doi: 10.34010/jamika.v12i2.7764.

R. Wadawadagi and V. Pagi, Sentiment analysis with deep neural networks: comparative study and performance assessment, Artif Intell Rev, vol. 53, no. 8, pp. 61556195, Dec. 2020, doi: 10.1007/s10462-020-09845-2.

Z. Singla, S. Randhawa, and S. Jain, Sentiment analysis of customer product reviews using machine learning, in 2017 International Conference on Intelligent Computing and Control (I2C2), IEEE, Jun. 2017, pp. 15. doi: 10.1109/I2C2.2017.8321910.

B. Laurensz and Eko Sediyono, Analisis Sentimen Masyarakat terhadap Tindakan Vaksinasi dalam Upaya Mengatasi Pandemi Covid-19, Jurnal Nasional Teknik Elektro dan Teknologi Informasi, vol. 10, no. 2, pp. 118123, May 2021, doi: 10.22146/jnteti.v10i2.1421.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Word2Vec Optimization on Bi-LSTM in Electric Car Sentiment Classification

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 JURNAL MEDIA INFORMATIKA BUDIDARMA

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



JURNAL MEDIA INFORMATIKA BUDIDARMA
STMIK Budi Darma
Secretariat: Sisingamangaraja No. 338 Telp 061-7875998
Email: mib.stmikbd@gmail.com

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