| Pub. Date | : April, 2023 |
|---|---|
| Product Name | : The IUP Journal of Management Research |
| Product Type | : Article |
| Product Code | : IJMR010423 |
| Author Name | : R M D G Rathnayaka and R A H M Rupasingha |
| Availability | : YES |
| Subject/Domain | : Arts & Humanities |
| Download Format | : PDF Format |
| No. of Pages | : 23 |
The Covid-19 pandemic had a negative impact on the standard of living of people across nations. There were also a lot of political changes, and therefore it is vital to look at how the public felt about these changes. During that time, there were a lot of Twitter posts and comments from people expressing their views. Twitter is a key social media platform for analyzing attitudes and offers helpful data for data mining. With the help of Twitter Application Program Interface (API), we gathered data from Twitter from 2020 to 2022. Data was labeled, pre-processed, and directed to the feature vector step using Term Frequency-Inverse Document Frequency (TF-IDF). The dataset was then fed into Machine Learning, and deep learning techniques, including Support Vector Machine (SVM), Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM), to construct a forecast paradigm for sentiment analysis. According to the categorization results, ANN outperformed SVM and LSTM and demonstrated higher accuracy (96.03%), better recall, precision, f-measure values, and lower error values. The findings are useful to gauge how people feel about political changes and quickly address significant issues. They also offer important lessons for the management of organizations.
The Covid-19 pandemic has had a devastating effect on people's health, society, economy, and environment on a global scale. The prolonged statewide lockdowns that followed the pandemic also had negative effects. An extensive economic and humanitarian crisis was brought on by the extreme lockdowns implemented in some countries. Covid-19 started spreading in the first three months of 2020, and by November 2020, it had spread to almost every country, had infected more than 50 million people globally, and had claimed more than 1.25 million lives (Forum,