AN EXPERIMENT USING AN LSTM MODEL FOR CLASSIFYING PUBLIC SENTIMENT TOWARDS THE ASTRAZENECA VACCINE

Hardian Oktavianto; Henny Wahyu Sulistyo; Taufiq Timur Warisaji; Guruh Wijaya

doi:10.35457/1d669j50

Authors

Hardian Oktavianto Universitas Muhammadiyah Jember https://orcid.org/0000-0002-2446-7401
Henny Wahyu Sulistyo Universitas Muhammadiyah Jember
Taufiq Timur Warisaji Universitas Muhammadiyah Jember
Guruh Wijaya Universitas Muhammadiyah Jember

DOI:

https://doi.org/10.35457/1d669j50

Keywords:

analisis sentimen, LSTM, media sosial, vaksin astrazeneca

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap vaksin AstraZeneca menggunakan metode Long Short-Term Memory. Data penelitian diperoleh dari media sosial X dengan rentang waktu 1 Februari 2024 hingga 15 Mei 2024, menghasilkan 251 data tweet yang telah melalui proses pembersihan, normalisasi, stopword removal, stemming, tokenisasi, dan padding. Model dibangun menggunakan arsitektur Sequential API TensorFlow Keras dengan lapisan Embedding, SpatialDropout1D, LSTM, dan Dense beraktivasi sigmoid. Evaluasi dilakukan pada tiga jenis distribusi data: original, oversampled, dan SMOTE. Hasil menunjukkan bahwa akurasi model pada ketiga kondisi data relatif sama, yaitu sebesar 65%, dengan nilai loss berkisar antara 64% hingga 67%. Hal ini mengindikasikan bahwa teknik penyeimbangan data seperti oversampling dan SMOTE tidak memberikan peningkatan performa signifikan dan bahkan dapat menimbulkan overfitting. Secara keseluruhan, penelitian ini membuktikan bahwa model LSTM mampu menangani ketidakseimbangan data dengan baik serta memberikan gambaran kuantitatif terhadap persepsi publik mengenai vaksin AstraZeneca.

Downloads

Download data is not yet available.

References

[1] N. A. M. Razali et al., “Opinion mining for national security: techniques, domain applications, challenges and research opportunities,” J. Big Data, vol. 8, no. 1, p. 150, 2021, doi: 10.1186/s40537-021-00536-5.

[2] L. Belcastro, R. Cantini, and F. Marozzo, “Knowledge Discovery from Large Amounts of Social Media Data,” Applied Sciences, vol. 12, no. 3. 2022. doi: 10.3390/app12031209.

[3] R. Refianti, A. B. Mutiara, and R. A. Putra, “A Lexicon-Based Long Short-Term Memory (LSTM) Model for Sentiment Analysis to Classify Halodoc Application Reviews on Google Playstore,” J. Appl. Data Sci. Vol 5, No 1 JANUARY 2024DO - 10.47738/jads.v5i1.160 , Jan. 2024, [Online]. Available: https://bright-journal.org/Journal/index.php/JADS/article/view/160

[4] G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artif. Intell. Rev., vol. 53, no. 8, pp. 5929–5955, 2020, doi: 10.1007/s10462-020-09838-1.

[5] Akshay Kaushal, Anandadeep Mandal, Diksha Khanna, and Animesh Acharjee, “Analysis of the opinions of individuals on the COVID-19 vaccination on social media,” Digit. Heal., vol. 9, p. 20552076231186250, Jan. 2023, doi: 10.1177/20552076231186246.

[6] R. Ida, S. E. Kinasih, S. N. Febriyanti, R. Puspa, M. Saud, and M. S. A. Bakar, “COVID-19 vaccine rumour and resistance in Indonesia: Analysing vaccine hesitancy and cultural myths circulated on online platforms,” Vacunas, vol. 25, no. 3, pp. 313–322, 2024, doi: https://doi.org/10.1016/j.vacun.2024.03.002.

[7] Y.-J. Choi, J. Lee, and S. Y. Paek, “Public Awareness and Sentiment toward COVID-19 Vaccination in South Korea: Findings from Big Data Analytics,” International Journal of Environmental Research and Public Health, vol. 19, no. 16. 2022. doi: 10.3390/ijerph19169914.

[8] K. L. Tan, C. P. Lee, and K. M. Lim, “A Survey of Sentiment Analysis: Approaches, Datasets, and Future Research,” Appl. Sci., vol. 13, no. 7, 2023, doi: 10.3390/app13074550.

[9] W. Aljedaani, E. Saad, F. Rustam, I. de la Torre Díez, and I. Ashraf, “Role of Artificial Intelligence for Analysis of COVID-19 Vaccination-Related Tweets: Opportunities, Challenges, and Future Trends,” Mathematics, vol. 10, no. 17. 2022. doi: 10.3390/math10173199.

[10] H. Wang et al., “Patterns of diverse and changing sentiments towards COVID-19 vaccines: a sentiment analysis study integrating 11 million tweets and surveillance data across over 180 countries,” J. Am. Med. Informatics Assoc., vol. 30, no. 5, pp. 923–931, May 2023, doi: 10.1093/jamia/ocad029.

[11] V. B. Vaghela, Z. Y. Noorani, K. Patel, P. G. Patel, H. D. Rajput, and M. Shah, “Aspect Based Sentiment Analysis Using Self-Attention Based LSTM Model with Word Embedding,” J. Comput. Sci., vol. 20, no. 10, 2024, doi: 10.3844/jcssp.2024.1195.1202.

[12] Aditi Chauhan, Yashika Kukkar, Preeti Nagrath, Kirti Gupta, and Jude D Hemanth, “Integrating LSTM and NLP techniques for essay generation,” Intell. Decis. Technol., vol. 18, no. 1, pp. 571–584, Feb. 2024, doi: 10.3233/IDT-230424.

[13] Y. I. Alzoubi, A. E. Topcu, and A. E. Erkaya, “Machine Learning-Based Text Classification Comparison: Turkish Language Context,” Applied Sciences, vol. 13, no. 16. 2023. doi: 10.3390/app13169428.

[14] H. Wang and L. Li, “Study on the Application of LSTM in Meteorological Element Prediction based on Computer Software,” J. Phys. Conf. Ser., vol. 1744, no. 2, p. 22034, 2021, doi: 10.1088/1742-6596/1744/2/022034.

[15] P. Anki, A. Bustamam, H. S. Al-Ash, and D. Sarwinda, “Intelligent Chatbot Adapted from Question and Answer System Using RNN-LSTM Model,” J. Phys. Conf. Ser., vol. 1844, no. 1, p. 12001, 2021, doi: 10.1088/1742-6596/1844/1/012001.

[16] F. Cascini et al., “Social media and attitudes towards a COVID-19 vaccination: A systematic review of the literature,” eClinicalMedicine, vol. 48, Jun. 2022, doi: 10.1016/j.eclinm.2022.101454.

[17] A. A. Jamali, C. Berger, and R. J. Spiteri, “Momentary Depressive Feeling Detection Using X (Formerly Twitter) Data: Contextual Language Approach,” JMIR AI, vol. 2, p. e49531, 2023, doi: 10.2196/49531.

[18] O. Narushynska, V. Teslyuk, A. Doroshenko, and M. Arzubov, “Data Sorting Influence on Short Text Manual Labeling Quality for Hierarchical Classification,” Big Data and Cognitive Computing, vol. 8, no. 4. 2024. doi: 10.3390/bdcc8040041.

[19] M. Francisco and J. L. Castro, “A Methodology to Quickly Perform Opinion Mining and Build Supervised Datasets Using Social Networks Mechanics,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 9, pp. 9797–9808, 2023, doi: 10.1109/TKDE.2023.3250822.

[20] A. B. Amendolara, D. Sant, H. G. Rotstein, and E. Fortune, “LSTM-based recurrent neural network provides effective short term flu forecasting,” BMC Public Health, vol. 23, no. 1, p. 1788, 2023, doi: 10.1186/s12889-023-16720-6.