Analisis Sentimen Masyarakat Pengguna Media Sosial Twitter Terhadap Motogp Mandalika Lombok Menggunakan Metode Bidirectional Encoder Representation From Transformers (BERT)
DOI:
https://doi.org/10.55606/isaintek.v6i1.103Keywords:
Sentiment Analysis, MotoGP, Mandalika, Lombok, BERTAbstract
The MotoGP One race in West Nusa Tenggara Lombok, Mandalika which was held on March 18 2022, received many responses or reactions from the public on social media, especially Twitter. There are those who agree and disagree about the holding of MotoGP in Mandalika, to find out the responses of the people who agree or disagree is needed that can process tweets data using the sentiment analysis method. The use of BERT (Bidirectional Encoder Representations from Transformers) for sentiment analysis produces a bidirectional language model that can understand the context of all words from a sentence. The dataset used goes through preprocessing stages such as case folding, data cleaning, tokenization, normalization, and removal of stopwords before sentiment analysis is carried out. This study uses several hyperparameters, namely a batch size of 32, the optimizer uses Adam with a learning rate of 3e-6 or 0.000003, and an epoch of 25. The evaluation results of the model obtain an accuracy of 55%. Precision for positive by 56%, neutral by 59%, and negative by 44%. Recall for positive is 74%, neutral is 29%, and negative is 54%. F1-score for positive is 64%, neutral is 38%, and negative is 48%.
References
Alammar, J. (n.d.). The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning). URL: https://jalammar.github.io/illustrated-bert/ [Tanggal Akses 20 Juli 2022]
Aliyah Salsabila, N., Ardhito Winatmoko, Y., Akbar Septiandri, A., & Jamal, A. (2018, November). Colloquial Indonesian lexicon. 2018 International Conference on Asian Language Processing (IALP). URL: http://dx.doi.org/10.1109/ialp.2018.8629151
Chen, M., Challita, U., Saad, W., Yin, C., & Debbah, M. (2019). Artificial neural networks-based machine learning for wireless networks: A tutorial. IEEE Communications Surveys & Tutorials, 21(4), 3039–3071. URL: https://doi.org/10.1109/comst.2019.2926625
Chollet, F. (2021). Deep Learning with Python, second edition. Simon and Schuster.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018, October 11). BERT: Pre-training of deep bidirectional transformers for language understanding. ArXiv.Org. URL: https://arxiv.org/abs/1810.04805
Eliasy, A. (2020, July 1). Fig. 2. The comparison between Recurrent Neural Network (RNN) and... Research Gate. URL:https://www.researchgate.net/figure/The-comparison-between-Recurrent-Neural-Network-RNN-and-Feed-Forward-Neural- Network_fig1_338672883
Gärtler, M., Khaydarov, V., Klöpper, B., & Urbas, L. (2021). The machine learning life cycle in chemical operations – status and open challenges. Chemie Ingenieur Technik, 93(12), 2063–2080.
URL: https://doi.org/10.1002/cite.202100134
Géron, A. (2019). Hands-On machine learning with Scikit-Learn, Keras, and TensorFlow, 2nd edition.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Khurana, D., Koli, A., Khatter, K., & Singh, S. (2022). Natural language processing: State of the art, current trends and challenges. Multimedia Tools and Applications. URL: https://doi.org/10.1007/s11042-022-13428-4
Koto, F., Lau, J. H., & Baldwin, T. (2021, September 10). IndoBERTweet: A pretrained language model for indonesian twitter with effective domain- specific vocabulary initialization. ArXiv.Org. URL:https://arxiv.org/abs/2109.04607
Nasteski, V. (2017). An overview of the supervised machine learning methods. HORIZONS.B, 4, 51–62. URL: https://doi.org/10.20544/horizons.b.04.1.17.p05
Saleh, Z. (2019, April 9). Artificial intelligence definition, ethics and standards. URL:https://www.researchgate.net/publication/332548325_Artificial_Intelligen ce_Definition_Ethics_and_Standards
Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019, May 14). How to fine-tune BERT for text classification? ArXiv.Org. URL: https://arxiv.org/abs/1905.05583
Yoo, B., & Rayz, J. T. (2021). Understanding emojis for sentiment analysis. The International FLAIRS Conference Proceedings, 34. URL:https://doi.org/10.32473/flairs.v34i1.128562
