Department of Physics, Indian Institute of Technology Guwahati, Guwahati, Assam, India.
School of Sciences, Fiji National University, Suva, Fiji.
PLoS One. 2023 Aug 1;18(8):e0288681. doi: 10.1371/journal.pone.0288681. eCollection 2023.
Topic modelling with innovative deep learning methods has gained interest for a wide range of applications that includes COVID-19. It can provide, psychological, social and cultural insights for understanding human behaviour in extreme events such as the COVID-19 pandemic. In this paper, we use prominent deep learning-based language models for COVID-19 topic modelling taking into account data from the emergence (Alpha) to the Omicron variant in India. Our results show that the topics extracted for the subsequent waves had certain overlapping themes such as governance, vaccination, and pandemic management while novel issues aroused in political, social and economic situations during the COVID-19 pandemic. We also find a strong correlation between the major topics with news media prevalent during the respective time period. Hence, our framework has the potential to capture major issues arising during different phases of the COVID-19 pandemic which can be extended to other countries and regions.
主题建模与创新的深度学习方法已经引起了广泛的关注，包括 COVID-19。它可以为理解人类在 COVID-19 大流行等极端事件中的行为提供心理、社会和文化方面的见解。在本文中，我们使用基于深度学习的知名语言模型对 COVID-19 主题建模进行研究，同时考虑了印度从出现（Alpha）到 Omicron 变异的数据。我们的结果表明，后续波次提取的主题存在某些重叠主题，例如治理、疫苗接种和大流行管理，而在 COVID-19 大流行期间的政治、社会和经济环境中出现了新的问题。我们还发现，主要主题与相应时间段内新闻媒体之间存在很强的相关性。因此，我们的框架有可能捕捉到 COVID-19 大流行不同阶段出现的主要问题，这可以扩展到其他国家和地区。
