EUVIMEDSkopri EUVIMED
Open access

Social Media Data Mining of Antitobacco Campaign Messages: Machine Learning Analysis of Facebook Posts

Shuo-Yu Lin iD, Xiaolu Cheng iD, Jun Zhang iD, Jaya Sindhu Yannam iD, Andrew J Barnes iD, J Randy Koch iD, Rashelle Hayes iD, Gilbert Gimm iD, Xiaoquan Zhao iD, Hemant Purohit iD, Hong Xue iD

Journal of Medical Internet Research · 2023

DOI: 10.2196/42863 ↗

At a glance

Journal article in Journal of Medical Internet Research, 2023. Written by Shuo-Yu Lin and 10 co-authors. Institution: Department of Health Administration and Policy, College of Public Health, George Mason University, Fairfax, VA, United States. Major MEDLINE topics: Social Media. Cited 21 times so far (Crossref); 49 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Social media platforms provide a valuable source of public health information, as one-third of US adults seek specific health information online. Many antitobacco campaigns have recognized such trends among youth and have shifted their advertising time and effort toward digital platforms. Timely evidence is needed to inform the adaptation of antitobacco campaigns to changing social media platforms.

Objective

In this study, we conducted a content analysis of major antitobacco campaigns on Facebook using machine learning and natural language processing (NLP) methods, as well as a traditional approach, to investigate the factors that may influence effective antismoking information dissemination and user engagement.

Methods

We collected 3515 posts and 28,125 associated comments from 7 large national and local antitobacco campaigns on Facebook between 2018 and 2021, including the Real Cost, Truth, CDC Tobacco Free (formally known as Tips from Former Smokers, where “CDC” refers to the Centers for Disease Control and Prevention), the Tobacco Prevention Toolkit, Behind the Haze VA, the Campaign for Tobacco-Free Kids, and Smoke Free US campaigns. NLP methods were used for content analysis, including parsimonious rule–based models for sentiment analysis and topic modeling. Logistic regression models were fitted to examine the relationship of antismoking message-framing strategies and viewer responses and engagement.

Results

We found that large campaigns from government and nonprofit organizations had more user engagements compared to local and smaller campaigns. Facebook users were more likely to engage in negatively framed campaign posts. Negative posts tended to receive more negative comments (odds ratio [OR] 1.40, 95% CI 1.20-1.65). Positively framed posts generated more negative comments (OR 1.41, 95% CI 1.19-1.66) as well as positive comments (OR 1.29, 95% CI 1.13-1.48). Our content analysis and topic modeling uncovered that the most popular campaign posts tended to be informational (ie, providing new information), where the key phrases included talking about harmful chemicals (n=43, 43%) as well as the risk to pets (n=17, 17%).

Conclusions

Facebook users tend to engage more in antitobacco educational campaigns that are framed negatively. The most popular campaign posts are those providing new information, with key phrases and topics discussing harmful chemicals and risks of secondhand smoke for pets. Educational campaign designers can use such insights to increase the reach of antismoking campaigns and promote behavioral changes.

Subjects

MeSH terms (MEDLINE)

Social MediaAdultAdolescentHumansAdvertisingInformation DisseminationPublic HealthData Mining

Author keywords

Facebookcontent analysisengagementnatural language processingpublic healthsmokingsocial mediasocial media campaigntobaccotobacco controltopic modelinguseyouth

Authors and institutions

  • Department of Health Administration and Policy, College of Public Health, George Mason University, Fairfax, VA, United States.
  • School of Computer Science and Engineering, Changshu Institute of Technology, Suzhou, Jiangsu Province, China.
  • Department of Physics and Engineering, College of Engineering and Science, Slippery Rock University of Pennsylvania, Slippery Rock, PA, United States.
  • Department of Health Behavior and Policy, School of Medicine, Virginia Commonwealth University, Richmond, VA, United States.
  • Department of Psychology, College of Humanities and Sciences, Virginia Commonwealth University, Richmond, VA, United States.
  • Center for the Study of Tobacco Products, Virginia Commonwealth University, Richmond, VA, United States.

ORCID profiles: Shuo-Yu Lin, Xiaolu Cheng, Jun Zhang, Jaya Sindhu Yannam, Andrew J Barnes, J Randy Koch, Rashelle Hayes, Gilbert Gimm, Xiaoquan Zhao, Hemant Purohit, Hong Xue

Cite

APA

Lin, S. Y., Cheng, X., Zhang, J., Yannam, J. S., Barnes, A. J., Koch, J. R., Hayes, R., Gimm, G., Zhao, X., Purohit, H., & Xue, H. (2023). Social Media Data Mining of Antitobacco Campaign Messages: Machine Learning Analysis of Facebook Posts. Journal of Medical Internet Research. https://doi.org/10.2196/42863

Vancouver

Lin SY, Cheng X, Zhang J, Yannam JS, Barnes AJ, Koch JR, et al. Social Media Data Mining of Antitobacco Campaign Messages: Machine Learning Analysis of Facebook Posts. Journal of Medical Internet Research. 2023. doi:10.2196/42863

BibTeX
@article{Lin2023,
  author = {Lin, Shuo-Yu and Cheng, Xiaolu and Zhang, Jun and Yannam, Jaya Sindhu and Barnes, Andrew J and Koch, J Randy and Hayes, Rashelle and Gimm, Gilbert and Zhao, Xiaoquan and Purohit, Hemant and Xue, Hong},
  title = {Social Media Data Mining of Antitobacco Campaign Messages: Machine Learning Analysis of Facebook Posts},
  journal = {Journal of Medical Internet Research},
  year = {2023},
  doi = {10.2196/42863}
}
Start for free →