A Pipeline to Understand Emerging Illness Via Social Media Data Analysis: Case Study on Breast Implant Illness

Background

A new illness can come to public attention through social media before it is medically defined, formally documented, or systematically studied. One example is a condition known as breast implant illness (BII), which has been extensively discussed on social media, although it is vaguely defined in the medical literature.

Objective

The objective of this study is to construct a data analysis pipeline to understand emerging illnesses using social media data and to apply the pipeline to understand the key attributes of BII.

Methods

We constructed a pipeline of social media data analysis using natural language processing and topic modeling. Mentions related to signs, symptoms, diseases, disorders, and medical procedures were extracted from social media data using the clinical Text Analysis and Knowledge Extraction System. We mapped the mentions to standard medical concepts and then summarized these mapped concepts as topics using latent Dirichlet allocation. Finally, we applied this pipeline to understand BII from several BII-dedicated social media sites.

Results

Our pipeline identified topics related to toxicity, cancer, and mental health issues that were highly associated with BII. Our pipeline also showed that cancers, autoimmune disorders, and mental health problems were emerging concerns associated with breast implants, based on social media discussions. Furthermore, the pipeline identified mentions such as rupture, infection, pain, and fatigue as common self-reported issues among the public, as well as concerns about toxicity from silicone implants.

Conclusions

Our study could inspire future studies on the suggested symptoms and factors of BII. Our study provides the first analysis and derived knowledge of BII from social media using natural language processing techniques and demonstrates the potential of using social media information to better understand similar emerging illnesses.

Use of social media in food safety in Saudi Arabia-a preliminary study

Over the past two decades, the rapid rise of social media has revolutionized the way we communicate and share information online. Social media platforms are not now only used extensively by individuals but also by businesses, governmental agencies, educational institutions, and many other organizations to deliver information to the public and, in return, collect information from that same audience. The preliminary study presented here offers valuable insights into how social media may be used to improve food safety standards. Today, food safety is still a major health challenge in the country, which occasionally faces unsafe food supply chains, an increased number of food borne outbreaks, and poor hygiene education. Social media may be used as a very valuable tool for people to access important information and more knowledge about food safety. The limited-scope survey presented here was conducted over the western part of Saudi Arabia and included 295 individuals of both genders, among various age groups. Participants responded to an online questionnaire about their use of social media to obtain information about food safety. Results showed that social media was indeed a major outlet for individuals to access information on food safety, with the top-ranked social media platforms being WhatsApp (M = 2.99) followed by Snapchat (M = 3.72), YouTube (M = 4.08), Instagram (M = 4.46), and Facebook (M = 4.81). Additionally, we found that the most trusted sources of information was the Saudi Food and Drug Authority (72.6%) and the Saudi Ministry of Health (55.4%). Participants most frequently sought epidemiological information (52.5%), quantitative risk estimates (23.1%), and information on the various types of foodborne infections (15.3%); they preferred the information to be in video format (67.5%), articles (57.6%), infographics (55.3%). Trustworthiness clearly emerged from the survey as an important consideration for individuals when accessing food safety information on social media.

Public perceptions of threats from mosquitoes in the U.S. using online media analytics

Mosquito-borne illnesses present a public health threat. This analysis quantifies general online mosquito media, and the Zika virus [ZIKV) specifically, from 7-20-2016 to 10-20-2018 in five U.S. geographies. The ZIKV sub-search comprised a shrinking share of online media about mosquitoes over time. Net sentiment, numerical scoring of search result positivity/negativity bounded between -100 and +100, was assessed. Mean net sentiment for the general mosquitoes search was -51; -55 for ZIKV. The ZIKV search revealed more variation in weekly net sentiment with a standard deviation of 14, compared to 10 for mosquitoes. Seventy-seven percent of the weeks had a net sentiment for the mosquito search that was more positive than the ZIKV search. For the 23% of the time the ZIKV search net sentiment was more positive than the general mosquito search, there were mentions of scientific advances, such as the potential for vaccine development associated with the post. Greater emphasis on public health threats from mosquitoes may be necessary to stimulate public action on mosquito-borne illness control. This analysis serves as an illustration of the potential for online/social media analysis to inform health officials of public interest/focus, and perhaps inform effective communication campaigns to combat public health threats.

Temporal and textual analysis of social media on collective discourses during the Zika virus pandemic

Background

While existing studies have investigated the role of social media on health-related communication, little is known about the potential differences between different users groups on different social media platforms in responses to a health event. This study sets out to explore the online discourse of governmental authorities and the public in Singapore during the recent Zika pandemic in 2016.

Methods

Social media data were extracted from Facebook and Twitter using retroactive keyword sourcing of the word “Zika” to search for posts and a location filter of “Singapore”. Government posts, public posts, and replies to these original posts were included in the temporal and textual analysis.

Results

Overall, Facebook contained more government and individual content whereas Twitter had more content from news media accounts. Though the relative volume of Zika content from different data sources paralleled the peaks and troughs of Zika activities across time, discourses from different data sources differed in their temporal patterns, such that the public discourse died down faster than the government discourse after the outbreak was declared. In addition, the content of discourses differed among data sources. While government discourse included factual information of the disease, public discourse contained more elements of care such as worry about the risks to pregnant women, and elements of community such as well-wishes to each other.

Conclusions

Our study demonstrates the temporal and content differences between user groups and social media platforms in social media conversations during the Zika pandemic. It suggests that future research should examine the collective discourse of a health event by investigating social media discourses within varied sources rather than focusing on a singular social media platform and by one particular type of users.

Moving from risk communication to food information communication and consumer engagement

Consumers in most developed countries have greater access to safer food than ever before, yet the issue of consumer perception on the safety of the food supply, the control infrastructure and existing and new process technologies is often not positive. A series of high profile food incidents, which have been ineffectively managed by both the regulators and the industry, and where there has been a failure to be open and transparent, have sensitised a proportion of consumers to scary stories about the food supply. There has been concomitant damage to consumer confidence in (i) the safety of food, (ii) the food industry's commitment to producing safe food and (iii) the authorities' ability to oversee the food chain. Threats to consumers' health and their genuine concerns have to be addressed with effective risk management and the protection of public health has to be paramount. Dealing with incorrect fears and misperceptions of risk has also to be addressed but achieving this is very difficult. The competencies of social scientists are needed to assist in gaining insights into consumer perceptions of risk, consumer behaviour and the determinants of trust. Conventional risk communication will not succeed on its own and more innovative and creative communication strategies are needed to engage with consumers using all available media channels in an open and transparent way. The digital media affords the opportunity to revolutionise engagement with consumers on food safety and nutrition-related issues.

Dynamics of Health Agency Response and Public Engagement in Public Health Emergency: A Case Study of CDC Tweeting Patterns During the 2016 Zika Epidemic

Background

Social media have been increasingly adopted by health agencies to disseminate information, interact with the public, and understand public opinion. Among them, the Centers for Disease Control and Prevention (CDC) is one of the first US government health agencies to adopt social media during health emergencies and crisis. It had been active on Twitter during the 2016 Zika epidemic that caused 5168 domestic noncongenital cases in the United States.

Objective

The aim of this study was to quantify the temporal variabilities in CDC’s tweeting activities throughout the Zika epidemic, public engagement defined as retweeting and replying, and Zika case counts. It then compares the patterns of these 3 datasets to identify possible discrepancy among domestic Zika case counts, CDC’s response on Twitter, and public engagement in this topic.

Methods

All of the CDC-initiated tweets published in 2016 with corresponding retweets and replies were collected from 67 CDC–associated Twitter accounts. Both univariate and multivariate time series analyses were performed in each quarter of 2016 for domestic Zika case counts, CDC tweeting activities, and public engagement in the CDC-initiated tweets.

Results

CDC sent out >84.0% (5130/6104) of its Zika tweets in the first quarter of 2016 when Zika case counts were low in the 50 US states and territories (only 560/5168, 10.8% cases and 662/38,885, 1.70% cases, respectively). While Zika case counts increased dramatically in the second and third quarters, CDC efforts on Twitter substantially decreased. The time series of public engagement in the CDC-initiated tweets generally differed among quarters and from that of original CDC tweets based on autoregressive integrated moving average model results. Both original CDC tweets and public engagement had the highest mutual information with Zika case counts in the second quarter. Furthermore, public engagement in the original CDC tweets was substantially correlated with and preceded actual Zika case counts.

Conclusions

Considerable discrepancies existed among CDC’s original tweets regarding Zika, public engagement in these tweets, and actual Zika epidemic. The patterns of these discrepancies also varied between different quarters in 2016. CDC was much more active in the early warning of Zika, especially in the first quarter of 2016. Public engagement in CDC’s original tweets served as a more prominent predictor of actual Zika epidemic than the number of CDC’s original tweets later in the year.

The Effect of Health Beliefs, Media Perceptions, and Communicative Behaviors on Health Behavioral Intention: An Integrated Health Campaign Model on Social Media

Social media have recently gained attention as a potential health campaign tool. This study examines this line of expectation concerning the role social media may play in health campaigns by testing an integrated health campaign model that combines insights from research on social media-specific perceptions and communicative behaviors in order to predict health behaviors. Specifically, this study aims to (a) develop a more holistic social media campaign model for predicting health behaviors in the social media context, (b) investigate how social media channel-related perceptions affect preventive health behaviors, and (c) investigate how communicative behaviors mediate perceptions and behavioral intention. The study conducted an online survey of 498 females who followed the Purple Ribbon Twitter campaign (@pprb), a cervical cancer prevention campaign. The results indicated that information acquisition mediated perceived risk's effect on intention. Information acquisition also mediated the relationships between intention and information selection and information transmission. On the other hand, social media-related perceptions indirectly impacted behavioral intention through communicative behaviors. The findings' theoretical and practical implications are discussed.

Analysis of Food Safety and Security Challenges in Emerging African Food Producing Areas through a One Health Lens: The Dairy Chains in Mali

Challenges posed by changes in livestock production in emerging food producing areas and demographic development and climate change require new approaches and responsibilities in the management of food chains. The increasingly recognized role of primary food producers requires the support of the scientific community to instruct effective approaches based on scientific data, tools, and expertise. Mali is an emerging food producing area, and this review covers (i) the dairy farming scenario and its environment, (ii) the role of dairy production in food security, including the greatly different animal rearing systems in the Sahel and tropical regions, (iii) risk management pillars as modern infrastructures, effective farmer organizations, and institutional systems to guarantee animal health and safety of products, and (iv) feasible interventions based on good practices and risk assessment at the farm level (e.g., sustainable use of fertilizers, feeds, veterinary drugs, and pesticides) to protect consumers from food safety hazards. Social innovation based on the empowerment of the primary food producers emerges as crucial for sustainable and safe food production. Sustainable policies should be supported by the mobilization of stakeholders of One Health, which is a science-based approach to linking human health and nutrition with the health and management of food producing animals and environmental safety. In the context of the complex, multifaceted scenario of Mali dairy production, this article presents how a cost-effective animal health and food safety scheme could be established in the dairy production chain. Because milk is a major commodity in this country, benefits could be derived in food security, public health, the resilience of the farming system, animal husbandry, and international trade.

Adverse Drug Reaction Identification and Extraction in Social Media: A Scoping Review

Background

The underreporting of adverse drug reactions (ADRs) through traditional reporting channels is a limitation in the efficiency of the current pharmacovigilance system. Patients’ experiences with drugs that they report on social media represent a new source of data that may have some value in postmarketing safety surveillance.

Objective

A scoping review was undertaken to explore the breadth of evidence about the use of social media as a new source of knowledge for pharmacovigilance.

Methods

Daubt et al’s recommendations for scoping reviews were followed. The research questions were as follows: How can social media be used as a data source for postmarketing drug surveillance? What are the available methods for extracting data? What are the different ways to use these data? We queried PubMed, Embase, and Google Scholar to extract relevant articles that were published before June 2014 and with no lower date limit. Two pairs of reviewers independently screened the selected studies and proposed two themes of review: manual ADR identification (theme 1) and automated ADR extraction from social media (theme 2). Descriptive characteristics were collected from the publications to create a database for themes 1 and 2.

Results

Of the 1032 citations from PubMed and Embase, 11 were relevant to the research question. An additional 13 citations were added after further research on the Internet and in reference lists. Themes 1 and 2 explored 11 and 13 articles, respectively. Ways of approaching the use of social media as a pharmacovigilance data source were identified.

Conclusions

This scoping review noted multiple methods for identifying target data, extracting them, and evaluating the quality of medical information from social media. It also showed some remaining gaps in the field. Studies related to the identification theme usually failed to accurately assess the completeness, quality, and reliability of the data that were analyzed from social media. Regarding extraction, no study proposed a generic approach to easily adding a new site or data source. Additional studies are required to precisely determine the role of social media in the pharmacovigilance system.

Digital and social media opportunities for dietary behaviour change

The way that people communicate, consume media and seek and receive information is changing. Forty per cent of the world's population now has an internet connection, the average global social media penetration is 39 % and 1·5 billion people have internet access via mobile phone. This large-scale move in population use of digital, social and mobile media presents an unprecedented opportunity to connect with individuals on issues concerning health. The present paper aims to investigate these opportunities in relation to dietary behaviour change. Several aspects of the digital environment could support behaviour change efforts, including reach, engagement, research, segmentation, accessibility and potential to build credibility, trust, collaboration and advocacy. There are opportunities to influence behaviour online using similar techniques to traditional health promotion programmes; to positively affect health-related knowledge, skills and self-efficacy. The abundance of data on citizens’ digital behaviours, whether through search behaviour, global positioning system tracking, or via demographics and interests captured through social media profiles, offer exciting opportunities for effectively targeting relevant health messages. The digital environment presents great possibilities but also great challenges. Digital communication is uncontrolled, multi-way and co-created and concerns remain in relation to inequalities, privacy, misinformation and lack of evaluation. Although web-based, social-media-based and mobile-based studies tend to show positive results for dietary behaviour change, methodologies have yet to be developed that go beyond basic evaluation criteria and move towards true measures of behaviour change. Novel approaches are necessary both in the digital promotion of behaviour change and in its measurement.