Evaluating COVID-19 public discourse for sentiment, topic, and geolocation analysis
Abstract This study examines public discourse on the COVID-19 pandemic using sentiment analysis, topic modeling, and geolocation analysis of Twitter data. This research aims to provide a multi-dimensional perspective on how different regions and demographics perceived and reacted to pandemic events....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-05-01
|
| Series: | Journal of Electrical Systems and Information Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s43067-025-00208-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract This study examines public discourse on the COVID-19 pandemic using sentiment analysis, topic modeling, and geolocation analysis of Twitter data. This research aims to provide a multi-dimensional perspective on how different regions and demographics perceived and reacted to pandemic events. Through sentiment analysis, over 57,000 tweets were categorized as positive, neutral, or negative, revealing public emotional responses over the pandemic’s progression. Topic modeling identified key themes, including public health measures, vaccination sentiments, and the impact of misinformation. Geolocation analysis further enhanced these insights by mapping sentiment and topic distributions across various regions, highlighting regional differences in pandemic-related discourse. Most studies primarily focused on sentiment trends, and they often lacked integration with geographic data, which is essential for understanding regional differences in public reactions. The integration of these methods with geotagging (geolocation) provided a comprehensive, user-friendly approach to large-scale data analysis, marking its importance in analysis public opinions based on geographic location for nation decision-making especially in healthcare services for such research. Hence, this study used hybrid data mining approaches and enhanced geolocation analysis to address this problem. Findings from this study contribute to understanding public responses to health crises, offering insights beneficial to policymakers, health professionals, and researchers in managing future pandemics. |
|---|---|
| ISSN: | 2314-7172 |