Investigating the COVID-19 vaccine discussions on Twitter through a multilayer network-based approach

Utilizing AI for extracting insights on post WHO's COVID-19 vaccination declaration from X (Twitter) social network

This study explores the use of artificial intelligence (AI) to analyze information from X (previously Twitter) feeds related to COVID-19, specifically focusing on the time following the World Health Organization's (WHO) vaccination announcement. This aspect of the pandemic has not been studied by other researchers focusing on vaccination news. By utilizing advanced AI algorithms, the research aims to examine a wealth of data, sentiments, and trends to enhance crisis management strategies effectively. Our methods involved collecting a dataset of tweets from December 2020 to July 2021. By using specific keywords strategically, we gathered a substantial 15.5 million tweets, focusing on important hashtags like #vaccine and #coronavirus while filtering out irrelevant replies and retweets. The assessment of three different machine learning models-BiLSTM, FFNN, and CNN - highlights the exceptional performance of BiLSTM, achieving an impressive F1-score of 0.84 on the test set, with Precision and Recall metrics at 0.85 and 0.83, respectively. The study provides a detailed visualization of global sentiments on COVID-19 topics, with a main goal of extracting insights to manage public health crises effectively. Sentiment labels were predicted using various classification models and categorized as positive, negative, and neutral for each country after adjusting for population differences. An important finding from the analysis is the variation in sentiments across regions, for instance, with Eastern European countries showing positive views on post-vaccination economic recovery, while China and the United States express negative opinions on the same topic.

A multilayered graph-based framework to explore behavioural phenomena in social media conversations

OBJECTIVE

Social media is part of current health communications. This research aims to delve into the effects of social contagion, biased assimilation, and homophily in building and changing health opinions on social media.

MATERIALS AND METHODS

Conversations about COVID-19 vaccination on English and Spanish Twitter are the case studies. A new multilayered graph-based framework supports the integrated analysis of content similarity within and across posts, users, and conversations to interpret contrasting and confluent user stances. Deep learning models are applied to infer stance. Graph centrality and homophily scores support the interpretation of information reproduction.

RESULTS

The results show that semantically related English posts tend to present a similar stance about COVID-19 vaccination (rstance = 0.51) whereas Spanish posts are more heterophilic (rstance = 0.38). Neither case showed evidence of homophily regarding user influence or vaccine hashtags. Graph filters for Pfizer and Astrazeneca with a similarity threshold of 0.85 show stance homophily in English scenarios (i.e. rstance = 0.45 and rstance = 0.58, respectively) and small homophily in Spanish scenarios (i.e. r = 0.12 and r = 0.3, respectively). Highly connected users are a minority and are not socially influential. Spanish conversations showed stance homophily, i.e. most of the connected conversations promote vaccination (rstance = 0.42), whereas English conversations are more likely to offer contrasting stances.

CONCLUSION

The methodology proposed for quantifying the impact of natural and intentional social behaviours in health information reproduction can be applied to any of the main social platforms and any given topic of conversation. Its effectiveness was demonstrated by two case studies describing English and Spanish demographic and sociocultural scenarios.

Unveiling Vaccine Hesitancy on Twitter: Analyzing Trends and Reasons during the Emergence of COVID-19 Delta and Omicron Variants

Given the high amount of information available on social media, the paper explores the degree of vaccine hesitancy expressed in English tweets posted worldwide during two different one-month periods of time following the announcement regarding the discovery of new and highly contagious variants of COVID-19-Delta and Omicron. A total of 5,305,802 COVID-19 vaccine-related tweets have been extracted and analyzed using a transformer-based language model in order to detect tweets expressing vaccine hesitancy. The reasons behind vaccine hesitancy have been analyzed using a Latent Dirichlet Allocation approach. A comparison in terms of number of tweets and discussion topics is provided between the considered periods with the purpose of observing the differences both in quantity of tweets and the discussed discussion topics. Based on the extracted data, an increase in the proportion of hesitant tweets has been observed, from 4.31% during the period in which the Delta variant occurred to 11.22% in the Omicron case, accompanied by a diminishing in the number of reasons for not taking the vaccine, which calls into question the efficiency of the vaccination information campaigns. Considering the proposed approach, proper real-time monitoring can be conducted to better observe the evolution of the hesitant tweets and the COVID-19 vaccine hesitation reasons, allowing the decision-makers to conduct more appropriate information campaigns that better address the COVID-19 vaccine hesitancy.

Deep learning-based credibility conversation detection approaches from social network

In recent years, the social networks that have become most exploited sources of information, such as Facebook, Instagram, LinkedIn, and Twitter, have been considered the main sources of non-credible information. False information on these social networks has a negative impact on the credibility of conversations. In this article, we propose a new deep learning-based credibility conversation detection approach in social network environments, called CreCDA. CreCDA is based on: (i) the combination of post and user features in order to detect credible and non-credible conversations; (ii) the integration of multi-dense layers to represent features more deeply and to improve the results; (iii) sentiment calculation based on the aggregation of tweets. In order to study the performance of our approach, we have used the standard PHEME dataset. We compared our approach with the main approaches we have studied in the literature. The results of this evaluation show the effectiveness of sentiment analysis and the combination of text and user levels to analyze conversation credibility. We recorded the mean precision of credible and non-credible conversations at 79%, the mean recall at 79%, the mean F1-score at 79%, the mean accuracy at 81%, and the mean G-Mean at 79%.

COVID-19 Testing, Vaccine Perceptions, and Trust among Hispanics Residing in an Underserved Community

The Borderplex region has been profoundly impacted by the COVID-19 pandemic. Borderplex residents live in low socioeconomic (SES) neighborhoods and lack access to COVID-19 testing. The purpose of this study was two-fold: first, to implement a COVID-19 testing program in the Borderplex region to increase the number of residents tested for COVID-19, and second, to administer a community survey to identify trusted sources of COVID-19 information and factors associated with COVID-19 vaccine uptake. A total of 4071 community members were tested for COVID-19, and 502 participants completed the survey. COVID-19 testing resulted in 66.8% (n = 2718) positive cases. The community survey revealed that the most trusted sources of COVID-19 information were doctors or health care providers (67.7%), government websites (e.g., CDC, FDA, etc.) (41.8%), and the World Health Organization (37.8%). Logistic regression models revealed several statistically significant predictors of COVID-19 vaccine uptake such as having a trusted doctor or health care provider, perceiving the COVID-19 vaccine to be effective, and perceiving that the COVID-19 vaccine does not cause side-effects. Findings from the current study highlight the need for utilizing an integrated, multifactorial approach to increase COVID-19 testing and to identify factors associated with COVID-19 vaccine uptake in underserved communities.

Modeling and Moderation of COVID-19 Social Network Chat

Negative social media usage during the COVID-19 pandemic has highlighted the importance of understanding the spread of misinformation and toxicity in public online discussions. In this paper, we propose a novel unsupervised method to discover the structure of online COVID-19-related conversations. Our method trains a nine-state Hidden Markov Model (HMM) initialized from a biclustering of 23 features extracted from online messages. We apply our method to 16,000 conversations (1.5 million messages) that took place on the Facebook pages of 15 Canadian newspapers following COVID-19 news items, and show that it can effectively extract the conversation structure and discover the main themes of the messages. Furthermore, we demonstrate how the PageRank algorithm and the conversation graph discovered can be used to simulate the impact of five different moderation strategies, which makes it possible to easily develop and test new strategies to limit the spread of harmful messages. Although our work in this paper focuses on the COVID-19 pandemic, the methodology is general enough to be applied to handle communications during future pandemics and other crises, or to develop better practices for online community moderation in general.

Impact of COVID-19 Pandemic on Mental Health and Socioeconomic Aspects in Greece

The global outbreak of the COVID-19 pandemic has spread worldwide, affecting almost all countries and territories. COVID-19 continues to impact various spheres of our life, such as the economy, industries, global market, agriculture, human health, health care, and many others. The aim of this study was to investigate the impact of the COVID-lockdowns on people's mental health in Greece. A descriptive, cross-sectional study was conducted in several urban, semi-urban and rural areas. The survey of 252 Greek people was conducted in spring 2022, and 46.8% of them were female and the other 53.2% were male. Ages were between 19 and 60 years old. Some of the main findings were that most of the participants feel their mental health got worse than before (about 80%), participants with kids were more affected than those who did not have any kids because they had bigger responsibilities and the pandemic might have caused them a lot of problems to deal with. The higher the income, the less they are affected, and people whose jobs did not change dramatically were also less likely to not be much mentally affected. Moreover, the percentage of smokers whose mental health became worse was greater than that among those who did not smoke. The same happened with those who consumed alcohol. Finally, we used the GBM algorithm to find three important predictors and we applied k-means to have a clear picture of the different clusters and how a number of participants are connected according to their answers.

Adolescent Distress: Is There a Vaccine? Social and Cultural Considerations during the COVID-19 Pandemic

The COVID-19 pandemic had an unprecedented impact on mental health. In particular, the impact on adolescents was likely significant due to vulnerability factors linked to this developmental stage and pre-existing conditions of hardship. The present work aimed at grasping the particular effects of the pandemic on social and cultural aspects of adolescence, providing a cross-sectional picture of this historical moment of contemporary youth culture. Further research is needed to verify the findings.

Anti-Vaccine Discourse on Social Media: An Exploratory Audit of Negative Tweets about Vaccines and Their Posters

As the anti-vaccination movement is spreading around the world, this paper addresses the ever more urgent need for health professionals, communicators and policy-makers to grasp the nature of vaccine mis/disinformation on social media. A one-by-one coding of 4511 vaccine-related tweets posted from the UK in 2019 resulted in 334 anti-vaccine tweets. Our analysis shows that (a) anti-vaccine tweeters are quite active and widely networked users on their own; (b) anti-vaccine messages tend to focus on the "harmful" nature of vaccination, based mostly on personal experience, values and beliefs rather than hard facts; (c) anonymity does not make a difference to the types of posted anti-vaccine content, but does so in terms of the volume of such content. Communication initiatives against anti-vaccination should (a) work closely with technological platforms to tackle anonymous anti-vaccine tweets; (b) focus efforts on mis/disinformation in three major arears (in order of importance): the medical nature of vaccines, the belief that vaccination is a tool of manipulation and control for money and power, and the "freedom of health choice" discourse against mandatory vaccination; and (c) go beyond common factual measures-such as detecting, labelling or removing fake news-to address emotions induced by personal memories, values and beliefs.

Public Health Policy Monitoring through Public Perceptions: A Case of COVID-19 Tweet Analysis

Since the start of the COVID-19 pandemic, government authorities have responded by issuing new public health policies, many of which were intended to contain its spread but ended up limiting economic and social activities. The citizen responses to these policies are diverse, ranging from goodwill to fear and anger. It is challenging to determine whether or not these public health policies achieved the intended impact. This requires systematic data collection and scientific studies, which can be very time-consuming. To overcome such challenges, in this paper, we provide an alternative approach to continuously monitor and dynamically make sense of how public health policies impact citizens. Our approach is to continuously collect Twitter posts related to COVID-19 policies and to analyze the public reactions. We have developed a web-based system that collects tweets daily and generates timelines and geographical displays of citizens’ “concern levels”. Tracking the public reactions towards different policies can help government officials assess the policy impacts in a more dynamic and real-time manner. For this paper, we collected and analyzed over 16 million tweets related to ten policies over a 10-month period. We obtained several findings; for example, the “COVID-19 (General)” and ”Ventilators” policies engendered the highest concern levels, while the “Face Coverings” policy caused the lowest. Nine out of ten policies exhibited significant changes in concern levels during the observation period.