BACKGROUND: Twitter, a popular social media outlet, has become a useful tool for the study of social behavior through user interactions called tweets. The geo-location and timestamp of tweets along with message content provide invaluable social and demographic information for an applied comparison of social behaviors across the world. OBJECTIVES: To determine the density and sentiments surrounding tobacco and e-cigarette tweets and link prevalence of word choices to tobacco and e-cigarette use at various localities. METHODS: All tweets with geo-spatial coordinates are salvaged from the twitter-feed, representing approximately 1% of the entire twitter-sphere, along with tweets mentioning Tobacco or Electronic Cigarettes from a 10% sample of twitter spanning 2012-2013. Pattern matching by tobacco and e-cigarette related keywords yield approximately 20,000 affiliated geo-tweets per month from North America. The emotionally charged words that contribute to the positivity of various subsets of regional tweets are quantitatively measured using hedonometrics. We examined the density of these behavioral tweet indicators by region and tested the relationship between tweeted smoking sentiments and time-space-type coordinates over a 6-month span using geo-data, as well as the change in sentiments over a two year span. RESULTS: For states with a high twitter prevalence, the ratio of tobacco tweets per state correlate to state smoking rate estimates. Over a 6-month span, the density of tobacco related tweets correlate to the CDC estimates of state smoking rates. Tobacco related tweets were collected over a two year span, and converted to each user’s local time using time-zone meta data in order to map the daily cycle of tobacco use in terms of frequency and happiness. Tweets mentioning electronic cigarette were predominately commercialized (⇡ 80%). These tweets were categorized in order to investigate the relationship between commercialized tweets and their effect on organic users. Our results illustrate significant variation in smoking sentiments by state and at varying regional scopes as well as over time. CONCLUSIONS: It is anticipated that real-time analysis of health behavior using twitter feeds will allow for more targeted forms of health policy planning and intervention. Regional density of tobacco and e-cigarette related tweets yield insight to the prevalence of tobacco usage per capita. Sentiment analysis across the twitter-sphere can help illuminate hazardous health behavioral trends and allows the possibility to help mediate poor health habits and potentially a number of health interventions in order to improve health consciousness and target medical interventions towards maximizing population health. Hedonometrics: Measuring the Happiness of a Text LabMT is a happiness distribution of the most frequently occurring 10,000 English words that were compiled through frequency distributions from literature,(Google Books), websites (Google Web Crawl), and Twitter. Surveys were created mimicking the self affective mannequin method, a sample of which is given above. Fifty participants were recruited using the online survey tool, Amazon Mechanical Turk, to identify the face that best matched the emotional response elicited by each word, which were then converted to a 9 point scale. On the numeric scale, 1 corresponded to the face with the largest frown and 9 to the face with the largest smile. The average happiness score, h avg , for each word was then calculated via the arithmetic mean of 50 user reported ratings per word. Using the average happiness scores of each word, the average positivity of a subset of tweets can be quantified and used to compare different tweet distributions. To increase the emotional signal, neutral words (4 h avg 6) are removed from the analysis. The standard approach to perform a hedonometric analysis on twitter is to create a happiness time-series. Outliers on the time series correspond to time-periods containing an overabundance of emotionally charged words. These outliers can then be investigated with word-shift graphs to help illuminate what is driving the emotional shift. 2012-2013 Twitter Happiness Time-series Using the happiness scores from LabMT, the average emotional rating of a corpus is calculated by tallying the appearance of words found in the intersection of the wordlist and a given corpus, in this case subsets of tweets. A weighted arithmetic mean of each word’s frequency, f word , and corresponding happiness score, h word for each of the N words in a text yields the average happiness score for the corpus, h more...