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

Abstract

Background: Health authorities can minimize the impact of an emergent infectious disease outbreak through effective and timely risk communication, which can build trust and adherence to subsequent behavioral messaging. Monitoring the psychological impacts of an outbreak, as well as public adherence to such messaging, is also important for minimizing long-term effects of an outbreak. Objective: We used social media data from Twitter to identify human behaviors relevant to COVID-19 transmission, as well as the perceived impacts of COVID-19 on individuals, as a first step toward real-time monitoring of public perceptions to inform public health communications. Methods: We developed a coding schema for 6 categories and 11 subcategories, which included both a wide number of behaviors as well codes focused on the impacts of the pandemic (eg, economic and mental health impacts). We used this to develop training data and develop supervised learning classifiers for classes with sufficient labels. Classifiers that performed adequately were applied to our remaining corpus, and temporal and geospatial trends were assessed. We compared the classified patterns to ground truth mobility data and actual COVID-19 confirmed cases to assess the signal achieved here. Results: We applied our labeling schema to approximately 7200 tweets. The worst-performing classifiers hadmore » F1 scores of only 0.18 to 0.28 when trying to identify tweets about monitoring symptoms and testing. Classifiers about social distancing, however, were much stronger, with F1 scores of 0.64 to 0.66. We applied the social distancing classifiers to over 228 million tweets. We showed temporal patterns consistent with real-world events, and we showed correlations of up to –0.5 between social distancing signals on Twitter and ground truth mobility throughout the United States. Conclusions: Behaviors discussed on Twitter are exceptionally varied. Twitter can provide useful information for parameterizing models that incorporate human behavior, as well as for informing public health communication strategies by describing awareness of and compliance with suggested behaviors.« less

Authors:

Daughton, Ashlynn R.  ^[1];

• Search DOE PAGES for author "Daughton, Ashlynn R."
• Search DOE PAGES for ORCID "0000-0003-1694-3268"

Shelley, Courtney D.  ^[1];

• Search DOE PAGES for author "Shelley, Courtney D."
• Search DOE PAGES for ORCID "0000-0002-5497-7453"

Barnard, Martha  ^[1];

• Search DOE PAGES for author "Barnard, Martha"
• Search DOE PAGES for ORCID "0000-0003-3677-3964"

Gerts, Dax  ^[1];

• Search DOE PAGES for author "Gerts, Dax"
• Search DOE PAGES for ORCID "0000-0001-9445-9573"

Watson Ross, Chrysm  ^[2];

• Search DOE PAGES for author "Watson Ross, Chrysm"
• Search DOE PAGES for ORCID "0000-0002-5989-3830"

Crooker, Isabel  ^[1];

• Search DOE PAGES for author "Crooker, Isabel"
• Search DOE PAGES for ORCID "0000-0001-5894-7799"

Nadiga, Gopal  ^[1];

• Search DOE PAGES for author "Nadiga, Gopal"
• Search DOE PAGES for ORCID "0000-0001-8226-8075"

Mukundan, Nilesh  ^[1];

• Search DOE PAGES for author "Mukundan, Nilesh"
• Search DOE PAGES for ORCID "0000-0002-8928-4809"

Vaquera Chavez, Nidia Yadira  ^[2];

• Search DOE PAGES for author "Vaquera Chavez, Nidia Yadira"
• Search DOE PAGES for ORCID "0000-0002-4382-5710"

Parikh, Nidhi  ^[1];

• Search DOE PAGES for author "Parikh, Nidhi"
• Search DOE PAGES for ORCID "0000-0002-5707-6124"

Pitts, Travis  ^[1];

• Search DOE PAGES for author "Pitts, Travis"
• Search DOE PAGES for ORCID "0000-0002-9381-9423"

Fairchild, Geoffrey  ^[1]

• Search DOE PAGES for author "Fairchild, Geoffrey"
• Search DOE PAGES for ORCID "0000-0001-5500-8120"

---

+ Show Author Affiliations

1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of New Mexico, Albuquerque, NM (United States)

Publication Date:

Tue May 25 00:00:00 EDT 2021

Research Org.:

Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Org.:

USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)

OSTI Identifier:

1827580

Report Number(s):

LA-UR-21-20074
Journal ID: ISSN 1438-8871

Grant/Contract Number:  

89233218CNA000001

Resource Type:

Accepted Manuscript

Journal Name:

Journal of Medical Internet Research

Additional Journal Information:

Journal Volume: 23; Journal Issue: 5; Journal ID: ISSN 1438-8871

Publisher:

JMIR Publications

Country of Publication:

United States

Language:

English

Subject:

60 APPLIED LIFE SCIENCES; information science; Twitter; social media; human behavior; infectious disease; COVID-19; coronavirus; infodemiology; infoveillance; social distancing; shelter-in-place; mobility; COVID-19 intervention