Social media sentiment analysis to monitor the performance of vaccination coverage during the early phase of the national COVID-19 vaccine rollout

When Infodemic Meets Epidemic: Systematic Literature Review

BACKGROUND

Epidemics and outbreaks present arduous challenges, requiring both individual and communal efforts. The significant medical, emotional, and financial burden associated with epidemics creates feelings of distrust, fear, and loss of control, making vulnerable populations prone to exploitation and manipulation through misinformation, rumors, and conspiracies. The use of social media sites has increased in the last decade. As a result, significant amounts of public data can be leveraged for biosurveillance. Social media sites can also provide a platform to quickly and efficiently reach a sizable percentage of the population; therefore, they have a potential role in various aspects of epidemic mitigation.

OBJECTIVE

This systematic literature review aimed to provide a methodical overview of the integration of social media in 3 epidemic-related contexts: epidemic monitoring, misinformation detection, and the relationship with mental health. The aim is to understand how social media has been used efficiently in these contexts, and which gaps need further research efforts.

METHODS

Three research questions, related to epidemic monitoring, misinformation, and mental health, were conceptualized for this review. In the first PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) stage, 13,522 publications were collected from several digital libraries (PubMed, IEEE Xplore, ScienceDirect, SpringerLink, MDPI, ACM, and ACL) and gray literature sources (arXiv and ProQuest), spanning from 2010 to 2022. A total of 242 (1.79%) papers were selected for inclusion and were synthesized to identify themes, methods, epidemics studied, and social media sites used.

RESULTS

Five main themes were identified in the literature, as follows: epidemic forecasting and surveillance, public opinion understanding, fake news identification and characterization, mental health assessment, and association of social media use with psychological outcomes. Social media data were found to be an efficient tool to gauge public response, monitor discourse, identify misleading and fake news, and estimate the mental health toll of epidemics. Findings uncovered a need for more robust applications of lessons learned from epidemic "postmortem documentation." A vast gap exists between retrospective analysis of epidemic management and result integration in prospective studies.

CONCLUSIONS

Harnessing the full potential of social media in epidemic-related tasks requires streamlining the results of epidemic forecasting, public opinion understanding, and misinformation detection, all while keeping abreast of potential mental health implications. Proactive prevention has thus become vital for epidemic curtailment and containment.

Negative sentiments toward anterior cruciate ligament injury prevention outweigh positive awareness discussions on social media

OBJECTIVES

The aim of this study is to understand the current public discussion surrounding anterior cruciate ligament (ACL) injury prevention on social media and determine factors that influence levels of public engagement.

METHODS

We performed a qualitative and quantitative cross-sectional analysis of ACL injury prevention techniques discussed on social media via the Twitter application programming interface (API). The Twitter API was queried from inception to May 2023 using keywords related to ACL injury and prevention. We conducted a thematic analysis of the posts and performed a sentiment analysis using natural language processing. A multivariable regression model was used to identify metadata that predicted higher engagement (media, links, tagging, hashtags).

RESULTS

A subset of 1823 unique posts was analyzed from 1701 unique accounts. Most posts were raising awareness about ACL injury prevention (n ​= ​733, 40.2%), followed by opinions on the topic (n ​= ​390, 21.4%), specific prevention techniques (n ​= ​289, 15.9%), personal experiences (n ​= ​272, 14.9%), and research (n ​= ​139, 7.6%). The majority consisted of posts from patients or caregivers (n ​= ​948, 55.7%), whereas healthcare providers accounted for 14.7% of posts. Posts containing media increased Tweet engagement count by an average of 6.1 (95% CI 2.8 to 9.4, p ​= ​0.00033) and posts discussing personal opinions increased engagement by 6.7 (95% CI 3.5 to 9.8, p ​= ​0.00004). On sentiment analysis of all included Tweets, 822 (45.1%) posts were positive, 309 (17.0%) were negative, and 692 (38.0%) were neutral. Sentiments expressed in posts related to ACL prevention were 2.8 times more negative compared to those discussing raising awareness.

CONCLUSIONS

There is active discussion about ACL injury prevention on Twitter. The use of visual media increased public engagement. We identified a potential knowledge gap between the available prevention techniques and the perspectives of athletes, highlighting the need for healthcare professionals to enhance their engagement with ACL injury prevention on social media.

LEVEL OF EVIDENCE

III.

"The reasons you believe …": An exploratory study of text driven evidence gathering and prediction from first responder records justifying state authorised intervention for mental health episodes

Objective First responders' mandatory reports of mental health episodes requiring emergency hospital care contain rich information about patients and their needs. In Queensland (Australia) much of the information contained in Emergency Examination Authorities (EEAs) remains unused. We propose and demonstrate a methodology to extract and translate vital information embedded in reports like EEAs and to use it to investigate the extreme propensity of incidence of serious mental health episodes. Methods The proposed method integrates clinical, demographic, spatial and free text information into a single data collection. The data is subjected to exploratory analysis for spatial pattern recognition leading to an observational epidemiology model for the association of maximum spatial recurrence of EEA episodes. Results Sentiment analysis revealed that among EEA presentations hospital and health service (HHS) region #4 had the lowest proportion of positive sentiments (18 %) compared to 33 % for HHS region #1 pointing to spatial differentiation of sentiments immanent in mandated free text which required more detailed analysis. At the postcode geographical level, we found that variation in maximum spatial recurrence of EEAs was significantly positively associated with spatial range of sentiments (0.29, p < 0.001) and the postcode-referenced sex ratio (0.45, p = 0.01). The volatility of sentiments significantly correlated with extremes of recurrence of EEA episodes. The predicted (probabilistic) incidence rate when mapped reflected this correlation. Conclusions The paper demonstrates the efficacy of integrating, machine extracted, human sentiments (as potential surrogates) with conventional exposure variables for evidence-based methods for mental health spatial epidemiology. Such insights from informatics-driven epidemiological observations may inform the strategic allocation of health system resources to address the highest levels of need and to improve the standard of care for mental patients while also enhancing their safe and humane treatment and management.

Investigation of Public Acceptance of Misinformation Correction in Social Media Based on Sentiment Attributions: Infodemiology Study Using Aspect-Based Sentiment Analysis

BACKGROUND

The proliferation of misinformation on social media is a significant concern due to its frequent occurrence and subsequent adverse social consequences. Effective interventions for and corrections of misinformation have become a focal point of scholarly inquiry. However, exploration of the underlying causes that affect the public acceptance of misinformation correction is still important and not yet sufficient.

OBJECTIVE

This study aims to identify the critical attributions that influence public acceptance of misinformation correction by using attribution analysis of aspects of public sentiment, as well as investigate the differences and similarities in public sentiment attributions in different types of misinformation correction.

METHODS

A theoretical framework was developed for analysis based on attribution theory, and public sentiment attributions were divided into 6 aspects and 11 dimensions. The correction posts for the 31 screened misinformation events comprised 33,422 Weibo posts, and the corresponding Weibo comments amounted to 370,218. A pretraining model was used to assess public acceptance of misinformation correction from these comments, and the aspect-based sentiment analysis method was used to identify the attributions of public sentiment response. Ultimately, this study revealed the causality between public sentiment attributions and public acceptance of misinformation correction through logistic regression analysis.

RESULTS

The findings were as follows: First, public sentiments attributed to external attribution had a greater impact on public acceptance than those attributed to internal attribution. The public associated different aspects with correction depending on the type of misinformation. The accuracy of the correction and the entity responsible for carrying it out had a significant impact on public acceptance of misinformation correction. Second, negative sentiments toward the media significantly increased, and public trust in the media significantly decreased. The collapse of media credibility had a detrimental effect on the actual effectiveness of misinformation correction. Third, there was a significant difference in public attitudes toward the official government and local governments. Public negative sentiments toward local governments were more pronounced.

CONCLUSIONS

Our findings imply that public acceptance of misinformation correction requires flexible communication tailored to public sentiment attribution. The media need to rebuild their image and regain public trust. Moreover, the government plays a central role in public acceptance of misinformation correction. Some local governments need to repair trust with the public. Overall, this study offered insights into practical experience and a theoretical foundation for controlling various types of misinformation based on attribution analysis of public sentiment.

COVID-19 vaccination perception and outcome: society sentiment analysis on twitter data in India

This study examines the perceptions and results of COVID-19 immunization using sentiment analysis of Twitter data from India. The tweets were collected from January 2021 to March 2023 using relevant hashtags and keywords. The dataset was pre-processed and cleaned before conducting sentiment analysis using Natural Language Processing techniques. Our results show that the overall sentiment toward COVID-19 vaccination in India has been positive, with a majority of tweets expressing support for vaccination and encouraging others to get vaccinated. However, we also identified some negative sentiments related to vaccine hesitancy, side effects, and mistrust in the government and pharmaceutical companies. We further analyzed the sentiment based on demographic factors such as gender, age, and location. The analysis revealed that the sentiment varied across different demographics, with some groups expressing more positive or negative sentiments than others. This study provides insights into the perception and outcomes of COVID-19 vaccination in India and highlights the need for targeted communication strategies to address vaccine hesitancy and increase vaccine uptake in specific demographics.

Users' Reactions to Announced Vaccines Against COVID-19 Before Marketing in France: Analysis of Twitter Posts

BACKGROUND

Within a few months, the COVID-19 pandemic had spread to many countries and had been a real challenge for health systems all around the world. This unprecedented crisis has led to a surge of online discussions about potential cures for the disease. Among them, vaccines have been at the heart of the debates and have faced lack of confidence before marketing in France.

OBJECTIVE

This study aims to identify and investigate the opinions of French Twitter users on the announced vaccines against COVID-19 through sentiment analysis.

METHODS

This study was conducted in 2 phases. First, we filtered a collection of tweets related to COVID-19 available on Twitter from February 2020 to August 2020 with a set of keywords associated with vaccine mistrust using word embeddings. Second, we performed sentiment analysis using deep learning to identify the characteristics of vaccine mistrust. The model was trained on a hand-labeled subset of 4548 tweets.

RESULTS

A set of 69 relevant keywords were identified as the semantic concept of the word "vaccin" (vaccine in French) and focused mainly on conspiracies, pharmaceutical companies, and alternative treatments. Those keywords enabled us to extract nearly 350,000 tweets in French. The sentiment analysis model achieved 0.75 accuracy. The model then predicted 16% of positive tweets, 41% of negative tweets, and 43% of neutral tweets. This allowed us to explore the semantic concepts of positive and negative tweets and to plot the trends of each sentiment. The main negative rhetoric identified from users' tweets was that vaccines are perceived as having a political purpose and that COVID-19 is a commercial argument for the pharmaceutical companies.

CONCLUSIONS

Twitter might be a useful tool to investigate the arguments for vaccine mistrust because it unveils political criticism contrasting with the usual concerns on adverse drug reactions. As the opposition rhetoric is more consistent and more widely spread than the positive rhetoric, we believe that this research provides effective tools to help health authorities better characterize the risk of vaccine mistrust.

Analysis of Differences in User Groups and Post Sentiment of COVID-19 Vaccine Hesitators in Chinese Social-Media Platforms

(1) Background: The COVID-19 epidemic is still global and no specific drug has been developed for COVID-19. Vaccination can both prevent infection and limit the spread of the epidemic. Eliminating hesitation to the COVID-19 vaccine and achieving early herd immunity is a common goal for all countries. However, efforts in this area have not been significant and there is still a long way to go to eliminate vaccine hesitancy. (2) Objective: This study aimed to uncover differences in the characteristics and sentiments of COVID-19 vaccine hesitators on Chinese social-media platforms and to achieve a classification of vaccine-hesitant groups. (3) Methods: COVID-19-vaccine-hesitation posts and user characteristics were collected on the Sina Microblog platform for posting times spanning one year, and posts were identified for hesitation types. Logistic regression was used to conduct user-group analysis. The differences in user characteristics between the various types of COVID-19 vaccine posts were analysed according to four user characteristics: gender, address type, degree of personal-information disclosure, and whether they followed health topics. Sentiment analysis was conducted using sentiment analysis tools to calculate the sentiment scores and sentiment polarity of various COVID-19 vaccine posts, and the K-W test was used to uncover the sentiment differences between various types of COVID-19-vaccine-hesitation posts. (4) Results: There are differences in the types of COVID-19-vaccine-hesitation posts posted by users with different characteristics, and different types of COVID-19-vaccine-hesitation posts differ in terms of sentiment. Differences in user attributes and user behaviors are found across the different COVID-19-vaccine-hesitation types. Ultimately, two COVID-19-vaccine-hesitant user groups were identified: Body-related and Non-bodily-related. Users who posted body-related vaccine-hesitation posts are more often female, disclose more personal information and follow health topics on social-media platforms. Users who posted non-bodily-related posts are more often male, disclose less personal information, and do not follow health topics. The average sentiment score for all COVID-19-vaccine-hesitant-type posts is less than 0.45, with negative-sentiment posts outweighing positive- and neutral-sentiment posts in each type, among which the "Individual rights" type is the most negative. (5) Conclusions: This paper complements the application of user groups in the field of vaccine hesitation, and the results of the analysis of group characteristics and post sentiment can help to provide an in-depth and comprehensive analysis of the concerns and needs of COVID-19 vaccine hesitators. This will help public-health agencies to implement more targeted strategies to eliminate vaccine hesitancy and improve their work related to the COVID-19 vaccine, with far-reaching implications for COVID-19-vaccine promotion and vaccination.

Public Discourse Surrounding Suicide during the COVID-19 Pandemic: An Unsupervised Machine Learning Analysis of Twitter Posts over a One-Year Period

Many studies have forewarned the profound emotional and psychosocial impact of the protracted COVID-19 pandemic. This study thus aimed to examine how individuals relate to suicide amid the COVID-19 pandemic from a global perspective via the public Twitter discourse around suicide and COVID-19. Original Twitter tweets from 1 February 2020 to 10 February 2021 were searched, with terms related to "COVID-19", "suicide", or "self-harm". An unsupervised machine learning approach and topic modelling were used to identify topics from unique tweets, with each topic further grouped into themes using manually conducted thematic analysis by the study investigators. A total of 35,904 tweets related to suicide and COVID-19 were processed into 42 topics and six themes. The main themes were: (1) mixed reactions to COVID-19 public health policies and their presumed impact on suicide; (2) biopsychosocial impact of COVID-19 pandemic on suicide and self-harm; (3) comparing mortality rates of COVID-19, suicide, and other leading causes of death; (4) mental health support for individuals at risk of suicide; (5) reported cases and public reactions to news related to COVID-19, suicide, and homicide; and (6) figurative usage of the word suicide. The general public was generally concerned about governments' responses as well as the perturbing effects on mental health, suicide, the economy, and at-risk populations.

Examining the Prevailing Negative Sentiments Related to COVID-19 Vaccination: Unsupervised Deep Learning of Twitter Posts over a 16 Month Period

Despite the demonstrated efficacy, safety, and availability of COVID-19 vaccines, efforts in global mass vaccination have been met with widespread scepticism and vaccine hesitancy or refusal. Understanding the reasons for the public's negative opinions towards COVID-19 vaccination using Twitter may help make new headways in improving vaccine uptake. This study, therefore, examined the prevailing negative sentiments towards COVID-19 vaccination via the analysis of public twitter posts over a 16 month period. Original tweets (in English) from 1 April 2021 to 1 August 2022 were extracted. A bidirectional encoder representations from transformers (BERT)-based model was applied, and only negative sentiments tweets were selected. Topic modelling was used, followed by manual thematic analysis performed iteratively by the study investigators, with independent reviews of the topic labels and themes. A total of 4,448,314 tweets were analysed. The analysis generated six topics and three themes related to the prevailing negative sentiments towards COVID-19 vaccination. The themes could be broadly understood as either emotional reactions to perceived invidious policies or safety and effectiveness concerns related to the COVID-19 vaccines. The themes uncovered in the present infodemiology study fit well into the increasing vaccination model, and they highlight important public conversations to be had and potential avenues for future policy intervention and campaign efforts.

Integrating Multiclass Light Weighted BiLSTM Model for Classifying Negative Emotions

With the continuous development of social networks, Weibo has become an essential platform for people to share their opinions and feelings in daily life. Analysis of users' emotional tendencies can be effectively applied to public opinion control, public opinion surveys, and product recommendations. However, the traditional deep learning algorithm often needs a large amount of data to be retained to obtain a better accuracy when faced with new work tasks. Given this situation, a multiclassification method of microblog negative sentiment based on MAML (model-agnostic metalearning) and BiLSTM (bidirectional extended short-term memory network) is proposed to represent the microblog text word vectorization and the combination of MAML and BiLSTM is constructed. The model of BiLSTM realizes the classification of negative emotions on Weibo and updates the parameters through machine gradient descent; the metalearner in MAML calculates the sum of the losses of multiple pieces of training, performs a second gradient descent, and updates the metalearner parameters. The updated metalearner can quickly iterate when faced with a new Weibo negative sentiment classification task. The experimental results show that compared with the prepopular model, on the Weibo negative sentiment dataset, the precision rate, recall rate, and F1 value are increased by 1.68 percentage points, 2.86 percentage points, and 2.27 percentage points, respectively.