Leveraging natural language processing and geospatial time series model to analyze COVID-19 vaccination sentiment dynamics on Tweets

Abstract

Objective To develop and apply a natural language processing (NLP)-based approach to analyze public sentiments on social media and their geographic pattern in the United States toward coronavirus disease 2019 (COVID-19) vaccination. We also aim to provide insights to facilitate the understanding of the public attitudes and concerns regarding COVID-19 vaccination. Methods We collected Tweet posts by the residents in the United States after the dissemination of the COVID-19 vaccine. We performed sentiment analysis based on the Bidirectional Encoder Representations from Transformers (BERT) and qualitative content analysis. Time series models were leveraged to describe sentiment trends. Key topics were analyzed longitudinally and geospatially. Results A total of 3 198 686 Tweets related to COVID-19 vaccination were extracted from January 2021 to February 2022. 2 358 783 Tweets were identified to contain clear opinions, among which 824 755 (35.0%) expressed negative opinions towards vaccination while 1 534 028 (65.0%) demonstrated positive opinions. The accuracy of the BERT model was 79.67%. The key hashtag-based topics include Pfizer, breaking, wearamask, and smartnews. The sentiment towards vaccination across the states showed manifest variability. Key barriers to vaccination include mistrust, hesitancy, safety concern, misinformation, and inequity. Conclusion We found that opinions toward the COVID-19 vaccination varied across different places and over time. This study demonstrates the potential of an analytical pipeline, which integrates NLP-enabled modeling, time series, and geospatial analyses of social media data. Such analyses could enable real-time assessment, at scale, of public confidence and trust in COVID-19 vaccination, help address the concerns of vaccine skeptics, and provide support for developing tailored policies and communication strategies to maximize uptake.

Analysis of the opinions of individuals on the COVID-19 vaccination on social media

“…Hence, with this study, we extend the previous findings and show that positive sentiments towards vaccination were rising only during 2021 and experienced a gradual decline thereafter. Moreover, our findings related to COVID-19 vaccination hesitancy were mostly in line with the past studies 88 , 89 with the majority of the concerns around side effects, mistrust, misinformation, culture, etc. However, we also show that conflicting advice, age, personal health, level of education, etc.…”

Implications for implementation and adoption of telehealth in developing countries: a systematic review of China’s practices and experiences

“…We also examined technological features that supported flexible modalities of telehealth services. Additionally, we explored processes that facilitated individual uptake of telehealth, such as involving family caregivers to assist children’s or older adults’ use of telehealth services 65 . Further, we proposed a framework comprising layers of infrastructures to support various levels of telehealth services.…”

Development and Application of Natural Language Processing on Unstructured Data in Hypertension: A Scoping Review

“…In addition, the advent and evolution of large language models (LLMs) stand as a cornerstone in the field of NLP, offering unprecedented capabilities in understanding, generating, and extracting meaningful information from vast swaths of unstructured data. [33] In the context of hypertension research, LLMs present a particularly promising avenue for innovation. These models, with their deep learning architectures, can analyze complex clinical narratives, decipher medical jargon, and identify nuanced patterns and indicators relevant to hypertension care that may elude traditional analysis methods.…”