ABSTRACT
Food is an integral part of our lives, cultures, and well-being, and is of major interest to public health. The collection of daily nutritional data involves keeping detailed diaries or periodic surveys and is limited in scope and reach. Alternatively, social media is infamous for allowing its users to update the world on the minutiae of their daily lives, including their eating habits. In this work we examine the potential of Twitter to provide insight into US-wide dietary choices by linking the tweeted dining experiences of 210K users to their interests, demographics, and social networks. We validate our approach by relating the caloric values of the foods mentioned in the tweets to the state-wide obesity rates, achieving a Pearson correlation of 0.77 across the 50 US states and the District of Columbia. We then build a model to predict county-wide obesity and diabetes statistics based on a combination of demographic variables and food names mentioned on Twitter. Our results show significant improvement over previous CHI research (Culotta 2014). We further link this data to societal and economic factors, such as education and income, illustrating that areas with higher education levels tweet about food that is significantly less caloric. Finally, we address the somewhat controversial issue of the social nature of obesity (Christakis & Fowler 2007) by inducing two social networks using mentions and reciprocal following relationships.
- Abisheva, A., Garimella, V. R. K., Garcia, D., and Weber, I. Who watches (and shares) what on youtube? and when?: using twitter to understand youtube viewership. In WSDM (2014). Google ScholarDigital Library
- Ahn, Y.-Y., Ahnert, S. E., Bagrow, J. P., and Barabási, A.-L. Flavor network and the principles of food pairing. Nature Scientific reports (2011).Google Scholar
- Aramaki, E., Maskawa, S., and Morita, M. Twitter catches the flu: Detecting influenza epidemics using twitter. In EMNLP (2011). Google ScholarDigital Library
- Bian, J., Topaloglu, U., and Yu, F. Towards large-scale twitter mining for drug-related adverse events. In SHB (2012). Google ScholarDigital Library
- Cawley, J., and Meyerhoefer, C. The medical care costs of obesity: an instrumental variables approach. Journal of health economics 31, 1 (2012), 219--230.Google Scholar
- Christakis, N. A., and Fowler, J. H. The spread of obesity in a large social network over 32 years. New England journal of medicine 357, 4 (2007), 370--379.Google Scholar
- Chunara, R., Bouton, L., Ayers, J. W., and Brownstein, J. S. Assessing the online social environment for surveillance of obesity prevalence. PloS one 8, 4 (2013), e61373.Google Scholar
- Cohen-Cole, E., and Fletcher, J. M. Is obesity contagious? social networks vs. environmental factors in the obesity epidemic. Journal of Health Economics 27, 5 (2008), 1382--1387.Google ScholarCross Ref
- Culotta, A. Lightweight methods to estimate influenza rates and alcohol sales volume from twitter messages. Language Resources and Evaluation (2013), 1--22. Google ScholarDigital Library
- Culotta, A. Estimating county health statistics with twitter. In CHI (2014). Google ScholarDigital Library
- Cutler, D. M., Glaeser, E. L., and Shapiro, J. M. Why have americans become more obese? Journal of Economic Perspectives 17 (2003), 93--118.Google ScholarCross Ref
- de Castro, J. M. Seasonal rhythms of human nutrient intake and meal pattern. Physiology & behavior 50, 1 (1991), 243--248.Google Scholar
- Donohew, L., Ray, E., and Donohew, L. Public health campaigns: Individual message strategies and a model. Communication and health: Systems and applications (1990), 136--152.Google Scholar
- Fischler, C. Food, self and identity. Social science information 27, 2 (1988), 275--292.Google Scholar
- Gershenson, C., Gasca-González, O. O., Delgado-Reyes, L., Pérez-Cruz, J. C., Orozco-Gómez, L. P., Hernández-Salazar, L., Moguel-Ancheita, S., Ramírez-Moreno, M. A., Morales-Cruz, M. V., Cortés-Gastélum, M. A., et al. Epidemiology and social networks. Cir Cir 79 (2011), 199--200.Google Scholar
- Haimson, O. L., Brubaker, J. R., and Hayes, G. R. Ddfseeks same: Sexual health-related language in online personal ads for men who have sex with men. In CHI (2014). Google ScholarDigital Library
- Kooti, F., Mason, W. A., Gummadi, K. P., and Cha, M. Predicting emerging social conventions in online social networks. In CIKM (2012). Google ScholarDigital Library
- Paul, M. J., and Dredze, M. You are what you tweet: Analyzing twitter for public health. In ICWSM (2011).Google Scholar
- Prier, K. W., Smith, M. S., Giraud-Carrier, C., and Hanson, C. L. Identifying health-related topics on twitter. In Social computing, behavioral-cultural modeling and prediction. Springer, 2011, 18--25. Google ScholarDigital Library
- Romero, D. M., Meeder, B., and Kleinberg, J. Differences in the mechanics of information diffusion across topics: idioms, political hashtags, and complex contagion on twitter. In WWW (2011). Google ScholarDigital Library
- Sadilek, A., and Kautz, H. Modeling the impact of lifestyle on health at scale. In WSDM (2013). Google ScholarDigital Library
- Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Dziurzynski, L., Agrawal, M., Park, G. J., Lakshmikanth, S. K., Jha, S., Seligman, M. E., Ungar, L., et al. Characterizing geographic variation in well-being using tweets. In ICWSM (2013).Google Scholar
- Silva, T. H., Vaz de Melo, P. O. S., Almeida, J., Musolesi, M., and Loureiro, A. You Are What You Eat (and Drink): Identifying Cultural Boundaries by Analyzing Food and Drink Habits in Foursquare. In ICWSM (2014).Google Scholar
- Takhteyev, Y., Gruzd, A., and Wellman, B. Geography of twitter networks. Social networks 34, 1 (2012), 73--81.Google Scholar
- Valente, T. W. Social network thresholds in the diffusion of innovations. Social networks 18, 1 (1996), 69--89.Google Scholar
- Wagner, C., Singer, P., and Strohmaier, M. Spatial and Temporal Patterns of Online Food Preferences. In WWW (Republic and Canton of Geneva, Switzerland, 2014). Google ScholarDigital Library
- West, R., White, R. W., and Horvitz, E. From cookies to cooks: insights on dietary patterns via analysis of web usage logs. In WWW (2013). Google ScholarDigital Library
- Xie, W., Li, C., Zhu, F., Lim, E.-P., and Gong, X. When a friend in twitter is a friend in life. In WebSci (2012). Google ScholarDigital Library
- Yom-Tov, E., Fernandez-Luque, L., Weber, I., and Crain, S. P. Pro-anorexia and pro-recovery photo sharing: a tale of two warring tribes. Journal of medical Internet research 14, 6 (2012).Google Scholar
- Zhu, Y.-X., Huang, J., Zhang, Z.-K., Zhang, Q.-M., Zhou, T., and Ahn, Y.-Y. Geography and similarity of regional cuisines in china. PloS one 8, 11 (2013), e79161.Google Scholar
Index Terms
- You Tweet What You Eat: Studying Food Consumption Through Twitter
Recommendations
#FoodPorn: Obesity Patterns in Culinary Interactions
DH '15: Proceedings of the 5th International Conference on Digital Health 2015We present a large-scale analysis of Instagram pictures taken at 164,753 restaurants by millions of users. Motivated by the obesity epidemic in the United States, our aim is three-fold: (i) to assess the relationship between fast food and chain ...
Disinformation Warfare: Understanding State-Sponsored Trolls on Twitter and Their Influence on the Web
WWW '19: Companion Proceedings of The 2019 World Wide Web ConferenceOver the past couple of years, anecdotal evidence has emerged linking coordinated campaigns by state-sponsored actors with efforts to manipulate public opinion on the Web, often around major political events, through dedicated accounts, or “trolls.” ...
A sentiment analysis of audiences on twitter: who is the positive or negative audience of popular twitterers?
ICHIT'11: Proceedings of the 5th international conference on Convergence and hybrid information technologyMicroblogging is a new informal communication medium of blogging that differs from a traditional blog in which content is much shorter. Microbloggers post about topics that describe their current status. Twitter is a popular microblogging service and ...
Comments