Next generation media monitoring: Global coverage of electronic nicotine delivery systems (electronic cigarettes) on Bing, Google and Twitter, 2013-2018

John W. Ayers, Mark Dredze, Eric C. Leas, Theodore L. Caputi, Jon Patrick Allem, Joanna E Cohen

Research output: Contribution to journalArticle

Abstract

News media monitoring is an important scientific tool. By treating news reporters as data collectors and their reports as qualitative accounts of a fast changing public health landscape, researchers can glean many valuable insights. Yet, there have been surprisingly few innovations in public health media monitoring, with nearly all studies relying on labor-intensive content analyses limited to a small number of media reports. We propose to advance this subfield by using scalable machine learning. In potentially the largest contemporary public health media monitoring study to date, we systematically characterize global news reports surrounding electronic cigarettes or electronic nicotine delivery systems (ENDS) using natural language processing techniques. News reports including ENDS terms (e.g., “electronic cigarettes”) from over 100,000 sources (all sources archived on Google News or Bing News, as well as all news articles shared on Twitter) were monitored for 1 January 2013 through 31 July 2018. The geographic and subject (e.g., prevalence, bans, quitting, warnings, marketing, prices, age, flavor and industry) foci of news articles, their popularity among readers who share news on social media, and the sentiment behind news articles were assessed algorithmically. Globally there were 86,872 ENDS news reports with coverage increasing from 8 (standard deviation [SD] = 8) stories per day in 2013 to 75 (SD = 56) stories per day during 2018. The focus of ENDS news spanned 148 nations, with the plurality focusing on the United States (34% of all news). Potentially overlooked hotspots of ENDS media activity included China, Egypt, Russia, Ukraine, and Paraguay. The most common subject was warnings about ENDS (18%), followed by bans on using ENDS (13%) and ENDS prices (9%). Flavor and age restrictions were the least covered news subjects (~1% each). Among different subject foci, reports on quitting cigarettes using ENDS had the highest probability of scoring in the top three deciles of popularity rankings. Moreover, ENDS news on quitting and prices had a more positive sentiment on average than news with other subject foci. Public health leaders can use these trends to stay abreast of how ENDS are portrayed in the media, and potentially how the public perceives ENDS. Because our analytical strategies are updated in near real time, we aim to make media monitoring part of standard practice to support evidence-based tobacco control in the future.

Original languageEnglish (US)
Article numbere0205822
JournalPLoS One
Volume13
Issue number11
DOIs
StatePublished - Nov 1 2018

Fingerprint

cigarettes
nicotine
Nicotine
Tobacco Products
electronics
Monitoring
monitoring
Public health
Public Health
public health
Flavors
Electronic Cigarettes
Natural language processing systems
Paraguay
Natural Language Processing
Social Media
flavor
Ukraine
Tobacco
news media

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Next generation media monitoring : Global coverage of electronic nicotine delivery systems (electronic cigarettes) on Bing, Google and Twitter, 2013-2018. / Ayers, John W.; Dredze, Mark; Leas, Eric C.; Caputi, Theodore L.; Allem, Jon Patrick; Cohen, Joanna E.

In: PLoS One, Vol. 13, No. 11, e0205822, 01.11.2018.

Research output: Contribution to journalArticle

Ayers, John W. ; Dredze, Mark ; Leas, Eric C. ; Caputi, Theodore L. ; Allem, Jon Patrick ; Cohen, Joanna E. / Next generation media monitoring : Global coverage of electronic nicotine delivery systems (electronic cigarettes) on Bing, Google and Twitter, 2013-2018. In: PLoS One. 2018 ; Vol. 13, No. 11.
@article{c95f444b210f4a4eb356b99b34f8aed6,
title = "Next generation media monitoring: Global coverage of electronic nicotine delivery systems (electronic cigarettes) on Bing, Google and Twitter, 2013-2018",
abstract = "News media monitoring is an important scientific tool. By treating news reporters as data collectors and their reports as qualitative accounts of a fast changing public health landscape, researchers can glean many valuable insights. Yet, there have been surprisingly few innovations in public health media monitoring, with nearly all studies relying on labor-intensive content analyses limited to a small number of media reports. We propose to advance this subfield by using scalable machine learning. In potentially the largest contemporary public health media monitoring study to date, we systematically characterize global news reports surrounding electronic cigarettes or electronic nicotine delivery systems (ENDS) using natural language processing techniques. News reports including ENDS terms (e.g., “electronic cigarettes”) from over 100,000 sources (all sources archived on Google News or Bing News, as well as all news articles shared on Twitter) were monitored for 1 January 2013 through 31 July 2018. The geographic and subject (e.g., prevalence, bans, quitting, warnings, marketing, prices, age, flavor and industry) foci of news articles, their popularity among readers who share news on social media, and the sentiment behind news articles were assessed algorithmically. Globally there were 86,872 ENDS news reports with coverage increasing from 8 (standard deviation [SD] = 8) stories per day in 2013 to 75 (SD = 56) stories per day during 2018. The focus of ENDS news spanned 148 nations, with the plurality focusing on the United States (34{\%} of all news). Potentially overlooked hotspots of ENDS media activity included China, Egypt, Russia, Ukraine, and Paraguay. The most common subject was warnings about ENDS (18{\%}), followed by bans on using ENDS (13{\%}) and ENDS prices (9{\%}). Flavor and age restrictions were the least covered news subjects (~1{\%} each). Among different subject foci, reports on quitting cigarettes using ENDS had the highest probability of scoring in the top three deciles of popularity rankings. Moreover, ENDS news on quitting and prices had a more positive sentiment on average than news with other subject foci. Public health leaders can use these trends to stay abreast of how ENDS are portrayed in the media, and potentially how the public perceives ENDS. Because our analytical strategies are updated in near real time, we aim to make media monitoring part of standard practice to support evidence-based tobacco control in the future.",
author = "Ayers, {John W.} and Mark Dredze and Leas, {Eric C.} and Caputi, {Theodore L.} and Allem, {Jon Patrick} and Cohen, {Joanna E}",
year = "2018",
month = "11",
day = "1",
doi = "10.1371/journal.pone.0205822",
language = "English (US)",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

TY - JOUR

T1 - Next generation media monitoring

T2 - Global coverage of electronic nicotine delivery systems (electronic cigarettes) on Bing, Google and Twitter, 2013-2018

AU - Ayers, John W.

AU - Dredze, Mark

AU - Leas, Eric C.

AU - Caputi, Theodore L.

AU - Allem, Jon Patrick

AU - Cohen, Joanna E

PY - 2018/11/1

Y1 - 2018/11/1

N2 - News media monitoring is an important scientific tool. By treating news reporters as data collectors and their reports as qualitative accounts of a fast changing public health landscape, researchers can glean many valuable insights. Yet, there have been surprisingly few innovations in public health media monitoring, with nearly all studies relying on labor-intensive content analyses limited to a small number of media reports. We propose to advance this subfield by using scalable machine learning. In potentially the largest contemporary public health media monitoring study to date, we systematically characterize global news reports surrounding electronic cigarettes or electronic nicotine delivery systems (ENDS) using natural language processing techniques. News reports including ENDS terms (e.g., “electronic cigarettes”) from over 100,000 sources (all sources archived on Google News or Bing News, as well as all news articles shared on Twitter) were monitored for 1 January 2013 through 31 July 2018. The geographic and subject (e.g., prevalence, bans, quitting, warnings, marketing, prices, age, flavor and industry) foci of news articles, their popularity among readers who share news on social media, and the sentiment behind news articles were assessed algorithmically. Globally there were 86,872 ENDS news reports with coverage increasing from 8 (standard deviation [SD] = 8) stories per day in 2013 to 75 (SD = 56) stories per day during 2018. The focus of ENDS news spanned 148 nations, with the plurality focusing on the United States (34% of all news). Potentially overlooked hotspots of ENDS media activity included China, Egypt, Russia, Ukraine, and Paraguay. The most common subject was warnings about ENDS (18%), followed by bans on using ENDS (13%) and ENDS prices (9%). Flavor and age restrictions were the least covered news subjects (~1% each). Among different subject foci, reports on quitting cigarettes using ENDS had the highest probability of scoring in the top three deciles of popularity rankings. Moreover, ENDS news on quitting and prices had a more positive sentiment on average than news with other subject foci. Public health leaders can use these trends to stay abreast of how ENDS are portrayed in the media, and potentially how the public perceives ENDS. Because our analytical strategies are updated in near real time, we aim to make media monitoring part of standard practice to support evidence-based tobacco control in the future.

AB - News media monitoring is an important scientific tool. By treating news reporters as data collectors and their reports as qualitative accounts of a fast changing public health landscape, researchers can glean many valuable insights. Yet, there have been surprisingly few innovations in public health media monitoring, with nearly all studies relying on labor-intensive content analyses limited to a small number of media reports. We propose to advance this subfield by using scalable machine learning. In potentially the largest contemporary public health media monitoring study to date, we systematically characterize global news reports surrounding electronic cigarettes or electronic nicotine delivery systems (ENDS) using natural language processing techniques. News reports including ENDS terms (e.g., “electronic cigarettes”) from over 100,000 sources (all sources archived on Google News or Bing News, as well as all news articles shared on Twitter) were monitored for 1 January 2013 through 31 July 2018. The geographic and subject (e.g., prevalence, bans, quitting, warnings, marketing, prices, age, flavor and industry) foci of news articles, their popularity among readers who share news on social media, and the sentiment behind news articles were assessed algorithmically. Globally there were 86,872 ENDS news reports with coverage increasing from 8 (standard deviation [SD] = 8) stories per day in 2013 to 75 (SD = 56) stories per day during 2018. The focus of ENDS news spanned 148 nations, with the plurality focusing on the United States (34% of all news). Potentially overlooked hotspots of ENDS media activity included China, Egypt, Russia, Ukraine, and Paraguay. The most common subject was warnings about ENDS (18%), followed by bans on using ENDS (13%) and ENDS prices (9%). Flavor and age restrictions were the least covered news subjects (~1% each). Among different subject foci, reports on quitting cigarettes using ENDS had the highest probability of scoring in the top three deciles of popularity rankings. Moreover, ENDS news on quitting and prices had a more positive sentiment on average than news with other subject foci. Public health leaders can use these trends to stay abreast of how ENDS are portrayed in the media, and potentially how the public perceives ENDS. Because our analytical strategies are updated in near real time, we aim to make media monitoring part of standard practice to support evidence-based tobacco control in the future.

UR - http://www.scopus.com/inward/record.url?scp=85056063126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056063126&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0205822

DO - 10.1371/journal.pone.0205822

M3 - Article

C2 - 30388126

AN - SCOPUS:85056063126

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

M1 - e0205822

ER -