scholarly journals Tracking COVID-19 Discourse on Twitter in North America: Topic Modeling and Aspect-based Sentiment Analysis (Preprint)

2020 ◽  
Author(s):  
Hyeju Jang ◽  
Emily Rempel ◽  
David Roth ◽  
Giuseppe Carenini ◽  
Naveed Z. Janjua

BACKGROUND Social media is a rich source where we can learn about people’s reactions to social issues. As COVID-19 has significantly impacted on people’s lives, it is essential to capture how people react to public health interventions and understand their concerns. OBJECTIVE We aim to investigate people’s reactions and concerns about COVID-19 in North America, especially focusing on Canada. METHODS We analyze COVID-19 related tweets using topic modeling and aspect-based sentiment analysis (ABSA), and interpret the results with public health experts. To generate insights on the effectiveness of specific public health interventions for COVID-19, we compare timelines of topics discussed with timing of implementation of interventions, synergistically including information on people’s sentiment about COVID-19 related aspects in our analysis. In addition, to further investigate anti-Asian racism, we compare timelines of sentiments for Asians and Canadians. RESULTS Topic modeling identified 20 topics and public health experts provided interpretations of the topics based on top-ranked words and representative tweets for each topic. The interpretation and timeline analysis showed that the discovered topics and their trend are highly related to public health promotions and interventions, such as physical distancing, border restrictions, hand washing, staying-home, and face coverings. After training the data using ABSA with human-in-the-loop, we obtained 545 aspect terms (e.g., “vaccines”, “economy”, and “masks”) and 60 opinion terms (e.g., “infectious”- negative, and “professional”- positive), which were used for inference of sentiments of 20 selected aspects. The results showed negative sentiments related to overall outbreak, misinformation, and Asians and positive sentiments related to physical distancing. CONCLUSIONS Analyses using Natural Language Processing (NLP) techniques with domain expert involvement can produce useful information for public health. This study is the first to analyze COVID-19 related tweets in Canada in comparison with tweets in the United States by using topic modeling and human-in-the-loop domain-specific aspect-based sentiment analysis. This kind of information could help public health agencies to understand public concerns as well as what public health messages are resonating in our populations who use Twitter, which can be helpful for public health agencies when designing a policy for new interventions.

10.2196/25431 ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. e25431
Author(s):  
Hyeju Jang ◽  
Emily Rempel ◽  
David Roth ◽  
Giuseppe Carenini ◽  
Naveed Zafar Janjua

Background Social media is a rich source where we can learn about people’s reactions to social issues. As COVID-19 has impacted people’s lives, it is essential to capture how people react to public health interventions and understand their concerns. Objective We aim to investigate people’s reactions and concerns about COVID-19 in North America, especially in Canada. Methods We analyzed COVID-19–related tweets using topic modeling and aspect-based sentiment analysis (ABSA), and interpreted the results with public health experts. To generate insights on the effectiveness of specific public health interventions for COVID-19, we compared timelines of topics discussed with the timing of implementation of interventions, synergistically including information on people’s sentiment about COVID-19–related aspects in our analysis. In addition, to further investigate anti-Asian racism, we compared timelines of sentiments for Asians and Canadians. Results Topic modeling identified 20 topics, and public health experts provided interpretations of the topics based on top-ranked words and representative tweets for each topic. The interpretation and timeline analysis showed that the discovered topics and their trend are highly related to public health promotions and interventions such as physical distancing, border restrictions, handwashing, staying home, and face coverings. After training the data using ABSA with human-in-the-loop, we obtained 545 aspect terms (eg, “vaccines,” “economy,” and “masks”) and 60 opinion terms such as “infectious” (negative) and “professional” (positive), which were used for inference of sentiments of 20 key aspects selected by public health experts. The results showed negative sentiments related to the overall outbreak, misinformation and Asians, and positive sentiments related to physical distancing. Conclusions Analyses using natural language processing techniques with domain expert involvement can produce useful information for public health. This study is the first to analyze COVID-19–related tweets in Canada in comparison with tweets in the United States by using topic modeling and human-in-the-loop domain-specific ABSA. This kind of information could help public health agencies to understand public concerns as well as what public health messages are resonating in our populations who use Twitter, which can be helpful for public health agencies when designing a policy for new interventions.


2015 ◽  
Vol 43 (S2) ◽  
pp. 45-48
Author(s):  
Browne Lewis

The information contained in this teaching module and the accompanying PowerPoint slides is appropriate for use in a survey public health law course or seminar. The purpose of this lesson is two-fold. The first objective is to provide law students with an overview of the authority public health agencies have to set and enforce policies necessary to keep the population healthy. The second objective is to inform law students about the legal constraints courts have placed upon the actions of those agencies. The module ends with a project designed to give law students the opportunity to apply the law to a “real world” situation.


Author(s):  
Laura Greisman ◽  
Barbara Koenig ◽  
Michele Barry

This chapter delves into the ethical issues surrounding the implementation of public health interventions for control of mosquito-borne illnesses. Emerging and reemerging mosquito-borne infections remain a public health threat worldwide, prompting public health agencies to strengthen individual and population-wide measures for mosquito control. Ethical issues surrounding surveillance activities and key public health interventions for mosquito control are discussed, including provision of insecticide-treated nets (ITNs), the spraying of aerial pesticides, and the introduction of genetically modified mosquitoes. A case study of Zika virus disease highlights specific ethical challenges surrounding the safety of insect repellent use in pregnancy and the complex issue of women’s reproductive rights arising in a fast-moving epidemic. The chapter emphasizes the need for community engagement at all levels of mosquito control interventions, and it highlights the disproportionate impact of mosquito-borne disease on the poor, calling to action the need to strengthen health systems in low- and middle-income countries.


Author(s):  
Natalie C Marshall ◽  
Maulik Baxi ◽  
Clayton MacDonald ◽  
Angela Jacobs ◽  
Christopher A Sikora ◽  
...  

Abstract Respiratory diphtheria is a potentially-fatal toxin-mediated disease that is rare among highly-vaccinated populations. Cutaneous infections with toxigenic Corynebacterium diphtheriae are most commonly linked to travel to an endemic region, though C. ulcerans has emerged as a predominant, locally-acquired cause of respiratory and cutaneous diphtheria in Western Europe. Recently, public health agencies from several highly-vaccinated regions expanded their guidelines to investigate toxigenic cutaneous diphtheria regardless of travel history. With relatively unknown epidemiology of C. diphtheriae in North America, and increasing diphtheria toxin testing over the last decade, this change could lead to substantial increases in public health investigations with unclear benefits. Therefore, this study examined the diagnostic and public health benefits of toxigenic cutaneous diphtheria investigations in the highly-vaccinated population of Alberta, Canada, where travel history is not required for cutaneous diphtheria investigations. Reviewing all C. diphtheriae isolates collected between 2010–2019, 82% were isolated from cutaneous sites and 5% were toxigenic. Three cases of toxigenic cutaneous disease were identified, none from patients with recent travel. Contact tracing identified asymptomatic C. diphtheriae colonization among 0–26% of close contacts, with identical isolate profiles among colonized contacts and primary cases. Overall, this study supports the exclusion of travel history as a prerequisite for public health investigations in North America. While further studies are needed to assess the prevalence and impact of endemic C. ulcerans in North America, this study suggests differing epidemiology of toxigenic corynebacteria compared to Europe and underscores the importance of including C. ulcerans in changing public health guidelines.


Urban Studies ◽  
1965 ◽  
Vol 2 (2) ◽  
pp. 195-196
Author(s):  
Andrew Semple

2011 ◽  
Vol 4 (0) ◽  
Author(s):  
Scott McNabb ◽  
Joseph Wamala ◽  
Anila Naz ◽  
Anna Hartrampf ◽  
Dan Samoly ◽  
...  

Author(s):  
Jonathan H. Marks

Collaboration with industry has become the paradigm in public health. Governments commonly develop close relationships with companies that are creating or exacerbating the very problems public health agencies are trying to solve. Nowhere is this more evident than in partnerships with food and soda companies to address obesity and diet-related noncommunicable diseases. The author argues that public-private partnerships and multistakeholder initiatives create webs of influence that undermine the integrity of public health agencies; distort public health research and policy; and reinforce the framing of public health problems and their solutions in ways that are least threatening to the commercial interests of corporate “partners.” We should expect multinational corporations to develop strategies of influence. But public bodies need to develop counter-strategies to insulate themselves from corporate influence in all its forms. The author reviews the ways in which we regulate public-public interactions (separation of powers) and private-private interactions (antitrust and competition laws), and argues for an analogous set of norms to govern public-private interactions. The book also offers a novel framework that is designed to help public bodies identify the systemic ethical implications of their existing or proposed relationships with industry actors. The book makes a compelling case that, in public health, the paradigm public-private interaction should be at arm’s length: separation, not collaboration. The author calls for a new paradigm to protect and promote public health while avoiding the ethical perils of partnership with industry.


Sign in / Sign up

Export Citation Format

Share Document