Siru Liu1, Jili Li2, Jialin Liu3. 1. Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, US. 2. West China Medical School, Sichuan University, Chengdu, CN. 3. Department of Medical Informatics, West China hospital, Sichuan University, No.37 Wainan guoxuexiang street, Chengdu, CN.
Abstract
BACKGROUND: The COVID-19 vaccine is considered to be the most promising approach to alleviate the pandemic. However, in recent surveys, acceptance of the COVID-19 vaccine has been low. To design more effective outreach interventions, there is an urgent need to understand public perceptions of COVID-19 vaccines. OBJECTIVE: Our objective is to analyze the potential of leveraging transfer learning to detect tweets containing opinions, attitudes, and behavioral intentions toward COVID-19 vaccines, and to explore temporal trends as well as automatically extract topics across a large number of tweets. METHODS: We developed machine learning and transfer learning models to classify tweets, followed by temporal analysis and topic modeling on a dataset of COVID-19 vaccine-related tweets posted from November 01, 2020 to January 31, 2021. We used the F1 values as the primary outcome to compare the performance of machine learning and transfer learning models. The statistical values and p-values from the Augmented Dickey-Fuller (ADF) test were used to assess whether users' perceptions changed over time. The main topics in tweets were extracted by latent Dirichlet allocation (LDA) analysis. RESULTS: We collected 2,678,372 tweets related to COVID-19 vaccines with 841,978 unique users and annotated 5,000 tweets. The F1 values of transfer learning models were 0.792 [0.789, 0.795], 0.578 [0.572, 0.0.584], and 0.614 [0.606, 0.622] for these three tasks, which significantly outperformed the machine learning models (logistic regression, random forest, and support vector machine). The prevalence of tweets containing attitudes and behavioral intentions varied significantly over time. Specifically, tweets containing positive behavioral intentions increased significantly in December 2020. In addition, we selected tweets in the following categories: positive attitudes, negative attitudes, positive behavioral intentions, and negative behavioral intentions. Then we identified 10 main topics and relevant terms for each category. CONCLUSIONS: Overall, we provided a method to automatically analyze the public understanding of COVID-19 vaccines from real-time data in social media, which can be used to tailor educational programs and other interventions to effectively promote the public acceptance of COVID-19 vaccines.
BACKGROUND: The COVID-19 vaccine is considered to be the most promising approach to alleviate the pandemic. However, in recent surveys, acceptance of the COVID-19 vaccine has been low. To design more effective outreach interventions, there is an urgent need to understand public perceptions of COVID-19 vaccines. OBJECTIVE: Our objective is to analyze the potential of leveraging transfer learning to detect tweets containing opinions, attitudes, and behavioral intentions toward COVID-19 vaccines, and to explore temporal trends as well as automatically extract topics across a large number of tweets. METHODS: We developed machine learning and transfer learning models to classify tweets, followed by temporal analysis and topic modeling on a dataset of COVID-19 vaccine-related tweets posted from November 01, 2020 to January 31, 2021. We used the F1 values as the primary outcome to compare the performance of machine learning and transfer learning models. The statistical values and p-values from the Augmented Dickey-Fuller (ADF) test were used to assess whether users' perceptions changed over time. The main topics in tweets were extracted by latent Dirichlet allocation (LDA) analysis. RESULTS: We collected 2,678,372 tweets related to COVID-19 vaccines with 841,978 unique users and annotated 5,000 tweets. The F1 values of transfer learning models were 0.792 [0.789, 0.795], 0.578 [0.572, 0.0.584], and 0.614 [0.606, 0.622] for these three tasks, which significantly outperformed the machine learning models (logistic regression, random forest, and support vector machine). The prevalence of tweets containing attitudes and behavioral intentions varied significantly over time. Specifically, tweets containing positive behavioral intentions increased significantly in December 2020. In addition, we selected tweets in the following categories: positive attitudes, negative attitudes, positive behavioral intentions, and negative behavioral intentions. Then we identified 10 main topics and relevant terms for each category. CONCLUSIONS: Overall, we provided a method to automatically analyze the public understanding of COVID-19 vaccines from real-time data in social media, which can be used to tailor educational programs and other interventions to effectively promote the public acceptance of COVID-19 vaccines.