Mining and Validating Social Media Data for COVID-19-Related Human Behaviors Between January and July 2020: Infodemiology Study

Content and User Engagement of Health-Related Behavior Tweets Posted by Mass Media Outlets From Spain and the United States Early in the COVID-19 Pandemic: Observational Infodemiology Study

BACKGROUND

During the early pandemic, there was substantial variation in public and government responses to COVID-19 in Europe and the United States. Mass media are a vital source of health information and news, frequently disseminating this information through social media, and may influence public and policy responses to the pandemic.

OBJECTIVE

This study aims to describe the extent to which major media outlets in the United States and Spain tweeted about health-related behaviors (HRBs) relevant to COVID-19, compare the tweeting patterns between media outlets of both countries, and determine user engagement in response to these tweets.

METHODS

We investigated tweets posted by 30 major media outlets (n=17, 57% from Spain and n=13, 43% from the United States) between December 1, 2019 and May 31, 2020, which included keywords related to HRBs relevant to COVID-19. We classified tweets into 6 categories: mask-wearing, physical distancing, handwashing, quarantine or confinement, disinfecting objects, or multiple HRBs (any combination of the prior HRB categories). Additionally, we assessed the likes and retweets generated by each tweet. Poisson regression analyses compared the average predicted number of likes and retweets between the different HRB categories and between countries.

RESULTS

Of 50,415 tweets initially collected, 8552 contained content associated with an HRB relevant to COVID-19. Of these, 600 were randomly chosen for training, and 2351 tweets were randomly selected for manual content analysis. Of the 2351 COVID-19-related tweets included in the content analysis, 62.91% (1479/2351) mentioned at least one HRB. The proportion of COVID-19 tweets mentioning at least one HRB differed significantly between countries (P=.006). Quarantine or confinement was mentioned in nearly half of all the HRB tweets in both countries. In contrast, the least frequently mentioned HRBs were disinfecting objects in Spain 6.9% (56/809) and handwashing in the United States 9.1% (61/670). For tweets from the United States mentioning at least one HRB, disinfecting objects had the highest median likes and retweets, whereas mask-wearing- and handwashing-related tweets achieved the highest median number of likes in Spain. Tweets from Spain that mentioned social distancing or disinfecting objects had a significantly lower predicted count of likes compared with tweets mentioning a different HRB (P=.02 and P=.01, respectively). Tweets from the United States that mentioned quarantine or confinement or disinfecting objects had a significantly lower predicted number of likes compared with tweets mentioning a different HRB (P<.001), whereas mask- and handwashing-related tweets had a significantly greater predicted number of likes (P=.04 and P=.02, respectively).

CONCLUSIONS

The type of HRB content and engagement with media outlet tweets varied between Spain and the United States early in the pandemic. However, content related to quarantine or confinement and engagement with handwashing was relatively high in both countries.

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.

Content and sentiment surveillance (CSI): A critical component for modeling modern epidemics

Comprehensive surveillance systems are the key to provide accurate data for effective modeling. Traditional symptom-based case surveillance has been joined with recent genomic, serologic, and environment surveillance to provide more integrated disease surveillance systems. A major gap in comprehensive disease surveillance is to accurately monitor potential population behavioral changes in real-time. Population-wide behaviors such as compliance with various interventions and vaccination acceptance significantly influence and drive the overall epidemic dynamics in the society. Original infoveillance utilizes online query data (e.g., Google and Wikipedia search of a specific content topic such as an epidemic) and later focuses on large volumes of online discourse data about the from social media platforms and further augments epidemic modeling. It mainly uses number of posts to approximate public awareness of the disease, and further compares with observed epidemic dynamics for better projection. The current COVID-19 pandemic shows that there is an urgency to further harness the rich, detailed content and sentiment information, which can provide more accurate and granular information on public awareness and perceptions toward multiple aspects of the disease, especially various interventions. In this perspective paper, we describe a novel conceptual analytical framework of content and sentiment infoveillance (CSI) and integration with epidemic modeling. This CSI framework includes data retrieval and pre-processing; information extraction via natural language processing to identify and quantify detailed time, location, content, and sentiment information; and integrating infoveillance with common epidemic modeling techniques of both mechanistic and data-driven methods. CSI complements and significantly enhances current epidemic models for more informed decision by integrating behavioral aspects from detailed, instantaneous infoveillance from massive social media data.

Using social media listening and data mining to understand travellers' perspectives on travel disease risks and vaccine-related attitudes and behaviours

BACKGROUND

Travellers can access online information to research and plan their expeditions/excursions, and seek travel-related health information. We explored German travellers' attitude and behaviour toward vaccination, and their travel-related health information seeking activities.

METHODS

We used two approaches: web 'scraping' of comments on German travel-related sites and an online survey. 'Scraping' of travel-related sites was undertaken using keywords/synonyms to identify vaccine- and disease-related posts. The raw unstructured text extracted from online comments was converted to a structured dataset using Natural Language Processing Techniques. Traveller personas were defined using K-means based on the online survey results, with cluster (i.e. persona) descriptions made from the most discriminant features in a distinguished set of observations. The web-scraped profiles were mapped to the personas identified. Travel and vaccine-related behaviours were described for each persona.

RESULTS

We identified ~2.6 million comments; ~880 k were unique and mentioned ~280 k unique trips by ~65 k unique profiles. Most comments were on destinations in Europe (37%), Africa (21%), Southeast Asia (12%) and the Middle East (11%). Eight personas were identified: 'middle-class family woman', 'young woman travelling with partner', 'female globe-trotter', 'upper-class active man', 'single male traveller', 'retired traveller', 'young backpacker', and 'visiting friends and relatives'. Purpose of travel was leisure in 82-94% of profiles, except the 'visiting friends and relatives' persona. Malaria and rabies were the most commented diseases with 12.7 k and 6.6 k comments, respectively. The 'middle-class family woman' and the 'upper-class active man' personas were the most active in online conversations regarding endemic disease and vaccine-related topics, representing 40% and 19% of comments, respectively. Vaccination rates were 54%-71% across the traveller personas in the online survey. Reasons for vaccination reluctance included perception of low risk to disease exposure (21%), price (14%), fear of side effects (12%) and number of vaccines (11%).

CONCLUSIONS

The information collated on German traveller personas and behaviours toward vaccinations should help guide counselling by healthcare professionals.

Measuring Public Concern About COVID-19 in Japanese Internet Users Through Search Queries: Infodemiological Study

Background

COVID-19 has disrupted lives and livelihoods and caused widespread panic worldwide. Emerging reports suggest that people living in rural areas in some countries are more susceptible to COVID-19. However, there is a lack of quantitative evidence that can shed light on whether residents of rural areas are more concerned about COVID-19 than residents of urban areas.

Objective

This infodemiology study investigated attitudes toward COVID-19 in different Japanese prefectures by aggregating and analyzing Yahoo! JAPAN search queries.

Methods

We measured COVID-19 concerns in each Japanese prefecture by aggregating search counts of COVID-19–related queries of Yahoo! JAPAN users and data related to COVID-19 cases. We then defined two indices—the localized concern index (LCI) and localized concern index by patient percentage (LCIPP)—to quantitatively represent the degree of concern. To investigate the impact of emergency declarations on people's concerns, we divided our study period into three phases according to the timing of the state of emergency in Japan: before, during, and after. In addition, we evaluated the relationship between the LCI and LCIPP in different prefectures by correlating them with prefecture-level indicators of urbanization.

Results

Our results demonstrated that the concerns about COVID-19 in the prefectures changed in accordance with the declaration of the state of emergency. The correlation analyses also indicated that the differentiated types of public concern measured by the LCI and LCIPP reflect the prefectures’ level of urbanization to a certain extent (ie, the LCI appears to be more suitable for quantifying COVID-19 concern in urban areas, while the LCIPP seems to be more appropriate for rural areas).

Conclusions

We quantitatively defined Japanese Yahoo users’ concerns about COVID-19 by using the search counts of COVID-19–related search queries. Our results also showed that the LCI and LCIPP have external validity.