Using Twitter to Examine Smoking Behavior and Perceptions of Emerging Tobacco Products

Abstract

BackgroundSocial media platforms such as Twitter are rapidly becoming key resources for public health surveillance applications, yet little is known about Twitter users’ levels of informedness and sentiment toward tobacco, especially with regard to the emerging tobacco control challenges posed by hookah and electronic cigarettes.ObjectiveTo develop a content and sentiment analysis of tobacco-related Twitter posts and build machine learning classifiers to detect tobacco-relevant posts and sentiment towards tobacco, with a particular focus on new and emerging products like hookah and electronic cigarettes.MethodsWe collected 7362 tobacco-related Twitter posts at 15-day intervals from December 2011 to July 2012. Each tweet was manually classified using a triaxial scheme, capturing genre, theme, and sentiment. Using the collected data, machine-learning classifiers were trained to detect tobacco-related vs irrelevant tweets as well as positive vs negative sentiment, using Naïve Bayes, k-nearest neighbors, and Support Vector Machine (SVM) algorithms. Finally, phi contingency coefficients were computed between each of the categories to discover emergent patterns.ResultsThe most prevalent genres were first- and second-hand experience and opinion, and the most frequent themes were hookah, cessation, and pleasure. Sentiment toward tobacco was overall more positive (1939/4215, 46% of tweets) than negative (1349/4215, 32%) or neutral among tweets mentioning it, even excluding the 9% of tweets categorized as marketing. Three separate metrics converged to support an emergent distinction between, on one hand, hookah and electronic cigarettes corresponding to positive sentiment, and on the other hand, traditional tobacco products and more general references corresponding to negative sentiment. These metrics included correlations between categories in the annotation scheme (phihookah-positive=0.39; phie-cigs-positive=0.19); correlations between search keywords and sentiment (χ2 4=414.50, P<.001, Cramer’s V=0.36), and the most discriminating unigram features for positive and negative sentiment ranked by log odds ratio in the machine learning component of the study. In the automated classification tasks, SVMs using a relatively small number of unigram features (500) achieved best performance in discriminating tobacco-related from unrelated tweets (F score=0.85).ConclusionsNovel insights available through Twitter for tobacco surveillance are attested through the high prevalence of positive sentiment. This positive sentiment is correlated in complex ways with social image, personal experience, and recently popular products such as hookah and electronic cigarettes. Several apparent perceptual disconnects between these products and their health effects suggest opportunities for tobacco control education. Finally, machine classification of tobacco-related posts shows a promising edge over strictly keyword-based approaches, yielding an improved signal-to-noise ratio in Twitter data and paving the way for automated tobacco surveillance ap...

Investigating the Documentation of Electronic Cigarette Use in the Veteran Affairs Electronic Health Record: A Pilot Study

“…Given the rapid rise in popularity of ecigarettes, and the lack of adequate public health surveillance systems currently focussing on these novel tobacco products, various methods and data sources have been used to understand changes in e-cigarette prevalence and usage patterns, including analysing search engine queries relevant to e-cigarettes (Ayers et al, 2011), mining social media data (Myslín et al, 2013;, and -the focus of this paper -analysing EHR data for e-cigarette related documentation (Winden et al, 2015).…”

Digital phenotyping and the development and delivery of health guidelines and behaviour change interventions

“…From the digital footprints left by individuals on services such as Twitter and Facebook, researchers can identify temporal and geographic patterns in a wide range of health behaviours, including smoking [9], drinking alcohol [10] and eating [11]. Specific approaches to utilizing social media data vary, from using occurrences of specified keywords (e.g.…”

“…Specific approaches to utilizing social media data vary, from using occurrences of specified keywords (e.g. 'alcohol') to target follow-up telephone interviews [10] to the application of machine-learning techniques to automatically identify words associated with behaviours of interest and, from these, to detect occurrences of individual instances of that behaviour [9].…”

Investigating Patient Attitudes Towards the use of Social Media Data to Augment Depression Diagnosis and Treatment: a Qualitative Study

“…Hanson et al (2013); Alvaro et al (2015); Powell et al (2016)), and investigating public attitudes towards health topics (e.g. Myslín et al (2013); Oscar et al (2017); Surian et al (2016)). In addition to its proven utility for addressing research questions in population health, social media may also have considerable potential to enhance clinical care, particularly mental health care, by providing frequent, naturalistic, behavioural data that can be used by mental health practitioners to track moods and symptoms over time, allowing mental health clinicians to triangulate diagnoses and to better understand patient progress between appointments, hence improving quality of care.…”