COVID-19 Twitter Data Analysis Using LSTM and BERT Techniques
COVID-19 Twitter Data Analysis Using LSTM and BERT Techniques |
||
 |
 |
|
| © 2024 by IJETT Journal | ||
| Volume-72 Issue-1 |
||
| Year of Publication : 2024 | ||
| Author : P. Dhanalakshmi, U. Janardhan Reddy, G. Ravikanth, Prasanthi Samathoti, Gandikota Ramu |
||
| DOI : 10.14445/22315381/IJETT-V72I1P122 | ||
How to Cite?
P. Dhanalakshmi, U. Janardhan Reddy, G. Ravikanth, Prasanthi Samathoti, Gandikota Ramu, "COVID-19 Twitter Data Analysis Using LSTM and BERT Techniques," International Journal of Engineering Trends and Technology, vol. 72, no. 1, pp. 219-228, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I1P122
Abstract
Sentiment analysis is a crucial task in understanding public opinion and perception towards a particular event or topic. The COVID-19 pandemic has greatly affected the world, and understanding public sentiment towards it is crucial for policymakers and organizations. In this paper, we introduced two efficient models for analyzing COVID-19-related tweets on categories such as WFH, Online learning and economy using BERT and Long Short-Term Memory techniques. Twitter data was collected using relevant keywords and hashtags related to COVID-19, such as WFH, Economy and Online Learning. The tweets were then tokenized and embedded using BERT, which provides a rich representation of the text by capturing contextual information. These embeddings were then passed on to a fully connected layer for the classification of the sentiment of the text. Similarly, the LSTM model was also used to classify the same tweets. The major reason for choosing LSTM and BERT for sentiment analysis over traditional machine learning algorithms is their ability to handle large datasets and long-term contextual dependencies. Experimental results show that the BERT model achieved an accuracy of 0.78, 0.85 and 0.92 on the Economy, WFH and Online learning datasets, respectively. At the same time, LSTM achieved an accuracy of 0.71, 0.76 and 0.81 on the Economy, WFH and Online learning datasets, respectively. The results clearly indicate that the BERT model outperformed the LSTM model in terms of accuracy. The high accuracy score demonstrates the effectiveness of the BERT model in understanding public sentiment towards the ongoing pandemic. The BERT model can be applied to other real-time public opinion analysis tasks and can provide valuable insights for decision-making. The results also indicate that BERT is a better choice than LSTM in this specific task of sentiment analysis on Twitter data.
Keywords
Long Short-Term Memory, Online tweets, Sentiment Analysis, Bidirectional Encoder Representations from Transformers.
References
[1] Yuxing Qi, and Zahratu Shabrina, “Sentiment Analysis using Twitter Data: A Comparative Application of Lexicon-and Machine-Learning-Based Approach,” Social Network Analysis and Mining, vol. 13, no. 1, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Kazi Nabiul Alam et al., “Deep Learning-Based Sentiment Analysis of COVID-19 Vaccination Responses from Twitter Data,” Computational and Mathematical Methods in Medicine, vol. 2021, pp. 1-15, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Mohammed Hasan Ali Al-Abyadh et al., “Deep Sentiment Analysis of Twitter Data Using a Hybrid Ghost Convolution Neural Network Model,” Computational Intelligence and Neuroscience, vol. 2022, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Burhan Bilen, and Fahrettin Horasan, “LSTM Network Based Sentiment Analysis for Customer Reviews,” Journal of Polytechnic, vol. 25, no. 3, pp. 959-966, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Rahul Kumar Chaurasiya et al., “Prediction of Twitter Sentiment Analysis by Using Naive Bayes Algorithm,” Journal of Big Data Technology and Business Analytics, vol. 2, no. 1, pp. 15-22, 2023.
[Google Scholar] [Publisher Link]
[6] Shrawan Kumar Trivedi, and Amrinder Singh, “Twitter Sentiment Analysis of App Based Online Food Delivery Companies,” Global Knowledge, Memory and Communication, vol. 70, no. 8/9, pp. 891-910, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Dharmendra Dangi, Dheeraj K. Dixit, and Amit Bhagat, “Sentiment Analysis of COVID-19 Social Media Data through Machine Learning,” Multimedia Tools and Applications, vol. 81, no. 29, pp. 42261-42283, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Syafrida Hafni Sahir et al., “Online Learning Sentiment Analysis during the Covid-19 Indonesia Pandemic Using Twitter Data,” IOP Conference Series: Materials Science and Engineering, vol. 1156, no. 1, pp. 1-7, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ashna Bali et al., “Consumer’s Sentiment Analysis of Popular Phone Brands and Operating System Preference,” International Journal of Computer Applications, vol. 155, no. 4, pp. 15-19, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Hernán Gil-Ramírez, and Rosa María Guilleumas-García, “Methodology for Sentiment Analysis in Twitter Posts About Mobile Learning,” South Florida Journal of Development, vol. 2, no. 2, pp. 2718-2728, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Anika Bhardwaj, and N. Natarajan, “Covid-19 Data Analysis using Machine Learning,” 3 rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), Greater Noida, India, pp. 2096-2099, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Langgao Cheng, “Urban Covid-19 Analysis and Prediction Based on Machine Learning and LSTM Models,” ISCTT 2022; 7th International Conference on Information Science, Computer Technology and Transportation, Xishuangbanna, China, pp. 1-4, 2022.
[Google Scholar] [Publisher Link]
[13] Suhaïl Madarbakusl, Abhishek Gobin, and Roopesh Kevin Sungkur, “Using Sentiment Analysis and Machine Learning to Collect the Perception of Online Learning,” Advances in Science and Engineering Technology International Conferences (ASET), Dubai, United Arab Emirates, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Hema Krishnan et al., “Machine Learning Based Sentiment Analysis of Coronavirus Disease Related Twitter Data,” 2 nd International Conference on Secure Cyber Computing and Communications (ICSCCC), Jalandhar, India, pp. 459-464, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Yassine Meraihi et al., “Machine Learning-Based Research for COVID-19 Detection, Diagnosis, and Prediction: A Survey,” SN Computer Science, vol. 3, no. 4, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Humaira Aslam, and Santanu Biswas, “Analysis of COVID-19 Death Cases Using Machine Learning,” SN Computer Science, vol. 4, no. 4, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]