Public reactions to e-cigarette regulations on Twitter: a text mining analysis

Background In May 2016, the Food and Drug Administration (FDA) issued a final rule that deemed e-cigarettes to be within their regulatory authority as a tobacco product. News and opinions about the regulation were shared on social media platforms, such as Twitter, which can play an important role in shaping the public’s attitudes. We analysed information shared on Twitter for insights into initial public reactions. Methods A text mining approach was used to uncover important topics among reactions to the e-cigarette regulations on Twitter. SAS Text Miner V.12.1 software was used for descriptive text mining to uncover the primary topics from tweets collected from May 1 to May 17 2016 using NUVI software to gather the data. Results A total of nine topics were generated. These topics reveal initial reactions to whether the FDA’s e-cigarette regulations will benefit or harm public health, how the regulations will impact the emerging e-cigarette market and efforts to share the news. The topics were dominated by negative or mixed reactions. Conclusions In the days following the FDA’s announcement of the new deeming regulations, the public reaction on Twitter was largely negative. Public health advocates should consider using social media outlets to better communicate the policy’s intentions, reach and potential impact for public good to create a more balanced conversation.

[1]  Richard Bonneau,et al.  Text Classification for Automatic Detection of E-Cigarette Use and Use for Smoking Cessation from Twitter: A Feasibility Pilot , 2016, PSB.

[2]  Heather Cole-Lewis,et al.  Social Listening: A Content Analysis of E-Cigarette Discussions on Twitter , 2015, Journal of medical Internet research.

[3]  Ramakanth Kavuluru,et al.  Toward automated e-cigarette surveillance: Spotting e-cigarette proponents on Twitter , 2016, J. Biomed. Informatics.

[4]  Cameron D. Norman,et al.  Vape, quit, tweet? Electronic cigarettes and smoking cessation on Twitter , 2016, International Journal of Public Health.

[5]  W. Chapman,et al.  Using Twitter to Examine Smoking Behavior and Perceptions of Emerging Tobacco Products , 2013, Journal of medical Internet research.

[6]  Gary B. Wilcox,et al.  Sudden Infant Death Syndrome and Safe Sleep on Twitter: Analysis of Influences and Themes to Guide Health Promotion Efforts , 2018, JMIR Pediatrics and Parenting.

[7]  Patric R. Spence,et al.  Expressions of risk awareness and concern through Twitter: On the utility of using the medium as an indication of audience needs , 2014, Comput. Hum. Behav..

[8]  J. Unger,et al.  Support for electronic cigarette regulations among California voters , 2016, Tobacco Control.

[9]  C. Bullen,et al.  Electronic cigarettes for smoking cessation and reduction. , 2014, The Cochrane database of systematic reviews.

[10]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[11]  S. Chapman,et al.  Smokers and non-smokers talk about regulatory options in tobacco control , 2006, Tobacco Control.

[12]  Brian A. King,et al.  Trends in awareness and use of electronic cigarettes among US adults, 2010-2013. , 2015, Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco.

[13]  Jay M Bernhardt,et al.  E-Cigarette Social Media Messages: A Text Mining Analysis of Marketing and Consumer Conversations on Twitter , 2016, JMIR public health and surveillance.

[14]  Cabral A. Bigman,et al.  Sociodemographic correlates of self-reported exposure to e-cigarette communications and its association with public support for smoke-free and vape-free policies: results from a national survey of US adults , 2014, Tobacco Control.

[15]  Annice E Kim,et al.  Using Twitter Data to Gain Insights into E-cigarette Marketing and Locations of Use: An Infoveillance Study , 2015, Journal of medical Internet research.

[16]  Christopher M. Danforth,et al.  Vaporous Marketing: Uncovering Pervasive Electronic Cigarette Advertisements on Twitter , 2015, PloS one.

[17]  A. Holton,et al.  Twitter as a source of vaccination information: content drivers and what they are saying. , 2013, American journal of infection control.

[18]  Cristine D Delnevo,et al.  Smokers’ attitudes and support for e-cigarette policies and regulation in the USA , 2015, Tobacco Control.

[19]  J. Brownstein,et al.  Twitter as a Sentinel in Emergency Situations: Lessons from the Boston Marathon Explosions , 2013, PLoS currents.

[20]  Mary Schwarz,et al.  Assessing Electronic Cigarette-Related Tweets for Sentiment and Content Using Supervised Machine Learning , 2015, Journal of medical Internet research.

[21]  S. Chapman,et al.  Tobacco control advocacy in the age of social media: using Facebook, Twitter and Change , 2012, Tobacco Control.

[22]  Michael J. Paul,et al.  Discovering Health Topics in Social Media Using Topic Models , 2014, PloS one.

[23]  D. Hammond,et al.  E-Cigarette Market Trends in Traditional U.S. Retail Channels, 2012-2013. , 2015, Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco.

[24]  E. Larson,et al.  Dissemination of health information through social networks: twitter and antibiotics. , 2010, American journal of infection control.

[25]  Jay M Bernhardt,et al.  Detecting themes of public concern: a text mining analysis of the Centers for Disease Control and Prevention's Ebola live Twitter chat. , 2015, American journal of infection control.

[26]  Jennifer L. Pearson,et al.  e-Cigarette awareness, use, and harm perceptions in US adults. , 2012, American journal of public health.

[27]  T. Glynn E‐cigarettes and the future of tobacco control , 2014, CA: a cancer journal for clinicians.

[28]  Johanna D. Moore,et al.  Twitter Sentiment Analysis: The Good the Bad and the OMG! , 2011, ICWSM.

[29]  Goutam Chakraborty,et al.  Text Mining and Analysis: Practical Methods, Examples, and Case Studies Using SAS , 2013 .

[30]  Yoonsang Kim,et al.  Garbage in, Garbage Out: Data Collection, Quality Assessment and Reporting Standards for Social Media Data Use in Health Research, Infodemiology and Digital Disease Detection , 2016, Journal of medical Internet research.

[31]  S. Emery,et al.  A cross-sectional examination of marketing of electronic cigarettes on Twitter , 2014, Tobacco Control.

[32]  S. Emery,et al.  Wanna know about vaping? Patterns of message exposure, seeking and sharing information about e-cigarettes across media platforms , 2014, Tobacco Control.

[33]  R. Malone The Race to a Tobacco Endgame , 2016, Tobacco Control.

[34]  Jay M Bernhardt,et al.  Identifying the public's concerns and the Centers for Disease Control and Prevention's reactions during a health crisis: An analysis of a Zika live Twitter chat. , 2016, American journal of infection control.