Tracking Mental Health and Symptom Mentions on Twitter During COVID-19

Guntuku, Sharath Chandra; Sherman, Garrick; Stokes, Daniel; Agarwal, Anish K.; Seltzer, Emily; Merchant, Raina M.; Ungar, Lyle H.

doi:10.1007/s11606-020-05988-8

Cited by 116 publications

(107 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, our temporal analyses pointed to a steady decline in people's expressed psychosocial concerns during the two month study period (Figure 1), which conforms with similar findings in Google search queries as stay-at-home orders and other COVID-19 related policy changes were implemented in the U.S. [104]. We note contemporary social computing research studying various aspects of the social media discourse related to COVID-19 [63,[105][106][107]. By providing complementary evidence to observations by Mackey et al [105] and Stokes et al [106] on expressed (mental health) concerns during the crisis, our work further underscores their findings using a comparable (control) dataset, reinforcing and providing empirical credibility to the impression that the COVID-19 pandemic has indeed caused or contributed directly to the mental health concerns that we describe.…”

Section: Comparison With Prior Worksupporting

confidence: 82%

Social Media Reveals Psychosocial Effects of the COVID-19 Pandemic

Saha

Torous

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The novel coronavirus disease 2019 (COVID-19) pandemic has caused several disruptions in personal and collective lives worldwide. The uncertainties surrounding the pandemic have also led to multi-faceted mental health concerns, which can be exacerbated with precautionary measures such as social distancing and self-quarantining, as well as societal impacts such as economic downturn and job loss. Despite noting this as a mental health tsunami, the psychological effects of the COVID-19 crisis remains unexplored at scale. Consequently, public health stakeholders are currently limited in identifying ways to provide timely and tailored support during these circumstances. Objective: Our work aims to provide insights regarding people's psychosocial concerns during the COVID-19 pandemic by leveraging social media data. We aim to study the temporal and linguistic changes in symptomatic mental health and support-seeking expressions in the pandemic context. Methods: We obtain 60M Twitter streaming posts originating from the U.S. from March, 24 to May, 25, 2020, and compare these with 40M posts from a comparable period in 2019 to causally attribute the effect of COVID-19 on people's social media self-disclosure. Using these datasets, we study people's self-disclosure on social media in terms of symptomatic mental health concerns and expressions seeking support. We employ transfer learning classifiers that identify the social media language indicative of mental health outcomes (anxiety, depression, stress, and suicidal ideation) and support (emotional and informational support). We then examine the changes in psychosocial expressions over time and language, comparing the 2020 and 2019 datasets. Results: We find that all of the examined psychosocial expressions have significantly increased during the COVID-19 crisis, mental health symptomatic expressions have increased by ~14%, and support seeking expressions have increased by 5%, both thematically related to COVID-19. We also observe a steady decline and eventual plateauing in these expressions during the COVID-19 pandemic, which may have been due to habituation or due to supportive policy measures enacted during this period. Our language analyses highlight that people express concerns that are contextually related to the COVID-19 crisis. Conclusions: We studied the psychosocial effects of the COVID-19 crisis by using social media data from 2020, finding that people's mental health symptomatic and support-seeking expressions significantly increased during the COVID-19 period as compared to similar data from 2019. However, this effect gradually lessened over time, suggesting that people adapted to the circumstances and their new normal. Our linguistic analyses revealed that people expressed mental health concerns regarding personal and professional challenges, healthcare and precautionary measures, and pandemic-related awareness. This work shows the potential to provide insights to mental healthcare and stakeholders and policymakers in planning and implementing measures to mitigate mental health risks amidst the health crisis.

show abstract

Section: Comparison With Prior Worksupporting

confidence: 82%

Social Media Reveals Psychosocial Effects of the COVID-19 Pandemic

Saha

Torous

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…During the early phases of the COVID-19 pandemic, the Penn Medicine Center for Digital Health and the World Well-Being Project launched a public-facing platform that uses machine learning approaches to synthesize data from Twitter about COVID-19 in real time. 5 Based on data from this platform and others and to enhance public awareness, the Washington State Department of Health posts weekly online behavioral health situation reports containing regional estimates of sentiment, loneliness, and anxiety. 6 This approach could be further harnessed to support situational awareness and enable more directed health messaging to address well-being and population-level mental health needs in response to COVID-19.…”

Section: Surveillance Of Digital Data To Inform Public Health Messagingmentioning

confidence: 99%

Public Health Messaging in an Era of Social Media

Merchant

South

Lurie

2021

JAMA

Self Cite

View full text Add to dashboard Cite

Public health organizations have always used messaging to educate the public in an attempt to control the spread of epidemic diseases. Early efforts that relied on word-of-mouth communication and poster campaigns transitioned to radio and television as those technologies emerged, yet these forms of communication likely have become less effective in a crowded, noisy, and confrontational online environment. Over the past decade, emerging digital platforms have become sophisticated, targeted, and responsive in reaching and influencing the public.Widespread physical distancing during the coronavirus disease 2019 (COVID-19) pandemic has limited informal social interactions and exposure to signage is considerably lessened as many people limit travel, order products online, and work from home. An effective messaging strategy will require meeting people where they are and through the information networks and devices they use for day-to-day interactions. As of December 27, 2020, more than 80 million people have contracted COVID-19 and 1.7 million have died. The need for effective public health messaging about community spread, prevention measures, and vaccines is more important than ever.Digital platforms are powerful yet underused tools for engaging the public and should be considered essential for public health preparedness, response, and recovery. This Viewpoint explores the following 4 strategies to advance public health messaging during this and future public health emergencies: deploying countermeasures for misinformation, surveillance of digital data to inform messaging, partnering with trusted messengers, and promoting equity through messaging.

show abstract

“…An analysis of sentiments expressed on social media after the national declaration of emergency compared to the same time period in 2019 demonstrates that the pandemic is having an unprecedented impact on well-being with stress, anxiety, and loneliness becoming markedly higher among the U.S. population (Guntuku et al, 2020). In the college population, the COVID-19 pandemic has had significant effects on students' anxiety and depression (Cao et al, 2020;Chirikov et al, 2020;Liu, Liu, & Zhong, 2020).…”

Section: Covid-19 In College Populationsmentioning

confidence: 99%

Understanding the Power of Social Media during COVID-19: Forming Social Norms for Drinking among Sexual Minority Gender Expansive College Women

Cerezo

Ramirez

O'Shaughnessy

et al. 2021

Journal of Homosexuality

View full text Add to dashboard Cite

Social media serves as a key mechanism for sexual minority young adults to connect with peers and to learn about COVID-19. We utilized focus groups to explore how sexual minority gender expansive college women (N= 28) engage with social media, including alcohol-related content on social networking sites. Two focus groups were held in-person during the month before the campus closed on March 10, 2020 due to a shelter-in-place mandate. Focus groups were then moved online, and also assessed how engagement with social media, including alcohol-related content, changed in response to COVID-19 at one month and two months into shelter-in-place. Using social media to connect with sexual and gender minority (SGM) content and community was a prominent theme across the three cohorts of data collection. Social drinking via social networking sites became increasingly prominent during shelter-in-place as a way to combat isolation, boredom, and the general stress of coping with COVID-19.

show abstract

Tracking Mental Health and Symptom Mentions on Twitter During COVID-19

Cited by 116 publications

References 6 publications

Social Media Reveals Psychosocial Effects of the COVID-19 Pandemic

Social Media Reveals Psychosocial Effects of the COVID-19 Pandemic

Public Health Messaging in an Era of Social Media

Understanding the Power of Social Media during COVID-19: Forming Social Norms for Drinking among Sexual Minority Gender Expansive College Women

Contact Info

Product

Resources

About