Comprehensive analytics of COVID-19 vaccine research: From topic modeling to topic classification

COVID-19 vaccine research has played a vital role in successfully controlling the pandemic, and the research surrounding the coronavirus vaccine is ever-evolving and accruing. These enormous efforts in knowledge production necessitate a structured analysis as secondary research to extract useful insights. In this study, comprehensive analytics was performed to extract these insights, which has moved the boundaries of data analytics in secondary research in the vaccine field by utilizing topic modeling, sentiment analysis, and topic classification based on the abstracts of related publications indexed in Scopus and PubMed. By applying topic modeling to 4803 abstracts filtered by this study criterion, 8 research arenas were identified by merging related topics. The extracted research areas were entitled "Reporting," "Acceptance," "Reaction," "Surveyed Opinions," "Pregnancy," "Titer of Variants," "Categorized Surveys," and "International Approaches." Moreover, the investigation of topics sentiments variations over time led to identifying researchers' attitudes and focus in various years from 2020 to 2022. Finally, a CNN-LSTM classification model was developed to predict the dominant topics and sentiments of new documents based on the 25 pre-determined topics with 75 % accuracy. The findings of this study can be utilized for future research design in this area by quickly grasping the structure of the current research on the COVID-19 vaccine. Through the findings of current research, a classification model was developed to classify the topic of a new article as one of the identified topics. Also, vaccine manufacturing firms will achieve a niche market by having a schema to invest in the gap of fields that have yet to be concentrated in extracted topics.