Ingmar Weber

Palakorn Achananuparp


To support people trying to lose weight and stay healthy, more and more fitness apps have sprung up including the ability to track both calories intake and expenditure. Users of such apps are part of a wider “quantified self” movement and many opt-in to publicly share their logged data. In this paper, we use public food diaries of more than 4,000 long-term active MyFitnessPal users to study the characteristics of a (un-)successful diet. Concretely, we train a machine learning model to predict repeatedly being over or under self-set daily calories goals and then look at which features contribute to the model’s prediction. Our findings include both expected results, such as the token “mcdonalds” or the category “dessert” being indicative for being over the calories goal, but also less obvious ones such as the difference between pork and poultry concerning dieting success, or the use of the “quick added calories” functionality being indicative of over-shooting calorie-wise. This study also hints at the feasibility of using such data for more in-depth data mining, e.g., looking at the interaction between consumed foods such as mixing protein- and carbohydrate-rich foods. To the best of our knowledge, this is the first systematic study of public food diaries. 



1. S. Abbar, Y. Mejova, and I. Weber. You tweet what you eat: Studying food consumption through
twitter. In Conference on Human Factors in Computing Systems (CHI), pages 3197–3206, 2015.
2. L. E. Burke, J. Wang, and M. A. Sevick. Self-monitoring in weight loss: A systematic review of
the literature. Journal of the American Dietetic Association, 111:92—-102, 2011.
3. A. Culotta. Estimating county health statistics with twitter. In Conference on Human Factors
in Computing Systems (CHI), pages 1335–1344, 2014.
4. A. Golay, A.-F. Allaz, J. Ybarra, P. Bianchi, S. Saraiva, N. Mensi, R. Gomis, and N. de Tonnac.
Similar weight loss with low-energy food combining or balanced diets. International Journal of
Obesity, 24(4):492–496, 2000.
5. M. A. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten. The WEKA
data mining software: an update. SIGKDD Explorations, 11(1):10–18, 2009.
6. T. Joachims. Making large-scale SVM learning practical. In B. Sch¨olkopf, C. Burges, and
A. Smola, editors, Advances in Kernel Methods – Support Vector Learning, chapter 11, pages
169–184. MIT Press, Cambridge, MA, 1999.
7. J. L. Kraschnewski, J. Boan, J. Esposito, N. E. Sherwood, E. B. Lehman, D. K. Kephart, and
C. N. Sciamanna. Long-term weight loss maintenance in the united states. International Journal
of Obesity, 34:1644–1654, 2010.
8. M. Kuebler, E. Yom-Tov, D. Pelleg, R. M. Puhl, and P. Muennig. When overweight is the normal
weight: An examination of obesity using a social media internet database. PLOS ONE, 8:e73479,
9. V. Li, D. W. McDonald, E. V. Eikey, J. Sweeney, J. Escajeda, G. Dubey, K. Riley, E. S. Poole, and
E. B. Hekler. Losing it online: Characterizing participation in an online weight loss community.
In Conference on Supporting Group Work (GROUP), pages 35–45, 2014.
10. J. A. Linde, R. W. Jeffery, S. J. Crow, K. L. Brelje, C. R. Pacanowski, K. L. Gavin, and D. J.
Smolenski. The tracking study: description of a randomized controlled trial of variations on
weight tracking frequency in a behavioral weight loss program. Contemporary Clinical Trials,
40:199–211, 2015.
11. J. Meyer, S. Simske, K. A. Siek, C. G. Gurrin, and H. Hermens. Beyond quantified self: Data for
wellbeing. In Conference on Human Factors in Computing Systems (CHI), pages 95–98, 2014.
12. K. Park, I. Weber, M. Cha, and C. Lee. Persistent sharing of fitness app status on twitter. In
omputer-Supported Cooperative Work and Social Computing (CSCW), page to appear, 2016.
13. H. E. Payne, C. Lister, J. H. West, , and J. M. Bernhardt. Behavioral functionality of mobile
apps in health interventions: A systematic review of the literature. JMIR Mhealth Uhealth, 3:e20,
14. D. Pelleg and A. W. Moore. X-means: Extending k-means with efficient estimation of the number
of clusters. In Conference on Machine Learning (ICML), pages 727–734, 2000
15. J. Rooksby, M. Rost, A. Morrison, and M. C. Chalmers. Personal tracking as lived informatics.
In Conference on Human Factors in Computing Systems (CHI), pages 1163–1172, 2014.
16. M. Rusin, E. Arsand, and G. Hartvigsen. Functionalities and input methods for recording food
intake: A systematic review. International Journal of Medical Informatics, 82:653–664, 2013.
17. C. N. Sciamanna, M. Kiernan, B. J. Rolls, J. Boan, H. Stuckey, D. Kephart, C. K. Miller,
G. Jensen, T. J. Hartmann, E. Loken, K. O. Hwang, R. J. Williams, M. A. Clark, J. R. Schubart,
A. M. Nezu, E. Lehman, and C. Dellasega. Practices associated with weight loss versus weight-
loss maintenance. American Journal of Preventive Medicine, 41:159–166, 2011.
18. C.-Y. Teng, Y.-R. Lin, and L. A. Adamic. Recipe recommendation using ingredient networks. In
Web Science Conference (WebSci), pages 298–307, 2012.
19. C. Wagner, P. Singer, and M. Strohmaier. The nature and evolution of online food preferences.
EPJ Data Science, 3(1), 2014.
20. C. Wagner, P. Singer, and M. Strohmaier. Spatial and temporal patterns of online food prefer-
ences. In World Wide Web Conference (WWW), pages 553–554, 2014.
21. R. West, R. W. White, and E. Horvitz. From cookies to cooks: insights on dietary patterns via
analysis of web usage logs. In World Wide Web Conference (WWW), pages 1399–1410, 2013.

The SELF Institute