Author(s):
- De Choudhury, Munmun
- Kumar, Mrinal
- Weber, Ingmar
Abstract:
The growing amount of data collected by quantified self tools and social media hold great potential for applications in personalized medicine. Whereas the first includes health-related physiological signals, the latter provides insights into a user’s behavior. However, the two sources of data have largely been studied in isolation. We analyze public data from users who have chosen to connect their MyFitnessPal and Twitter accounts. We show that a user’s diet compliance success, measured via their self-logged food diaries, can be predicted using features derived from social media: linguistic, activity, and social capital. We find that users with more positive affect and a larger social network are more successful in succeeding in their dietary goals. Using a Granger causality methodology, we also show that social media can help predict daily changes in diet compliance success or failure with an accuracy of 77%, that improves over baseline techniques by 17%. We discuss the implications of our work in the design of improved health interventions for behavior change.
Document: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5565732/
References:
References
1. Abbar Sofiane, Mejova Yelena, Weber Ingmar. You Tweet What You Eat: Studying Food Consumption Through Twitter; Conference on Human Factors in Computing Systems (CHI); 2015. pp. 3197–3206. [Google Scholar]
2. Adams Phil, Rabbi Mashfiqui, Rahman Tauhidur, Matthews Mark, Voida Amy, Gay Geri, Choudhury Tanzeem, Voida Stephen. Towards personal stress informatics: comparing minimally invasive techniques for measuring daily stress in the wild. PervasiveHealth. 2014:72–79. [Google Scholar]
3. Akbar Fatema, Weber Ingmar. #Sleep as Android: Feasibility of Using Sleep Logs on Twitter for Sleep Studies. IEEE ICHI. 2016 http://arxiv.org/abs/1607.06359.
4. Al’Absi M, Arnett DK. Adrenocortical responses to psychological stress and risk for hypertension. Biomedicine & pharmacotherapy. 2000;54(5):234–244. 2000. [PubMed] [Google Scholar]
5. Ashley Euan A. The precision medicine initiative: a new national effort. JAMA. 2015;313(21):2119–2120. 2015. [PubMed] [Google Scholar]
6. Brage Søren, Brage Niels, Franks PW, Ekelund U, Wareham NJ. Reliability and validity of the combined heart rate and movement sensor Actiheart. European journal of clinical nutrition. 2005;59(4):561–570. 2005. [PubMed] [Google Scholar]
7. Chancellor Stevie, Lin Zhiyuan (Jerry), Goodman Erica, Zerwas Stephanie, De Choudhury Munmun. Quantifying and Predicting Mental Illness Severity in Online Pro-Eating Disorder Communities; CSCW; 2016. pp. 1171–1184. [Google Scholar]
8. Chen Fanglin, Wang Rui, Zhou Xia, Campbell Andrew T. My smartphone knows i am hungry; Proceedings of the 2014 workshop on physical analytics; 2014. pp. 9–14. [Google Scholar]
9. Chung Cindy, Pennebaker James W. The psychological functions of function words. Social communication. 2007;(2007):343–359. [Google Scholar]
10. Clawson James, Pater Jessica A, Miller Andrew D, Mynatt Elizabeth D, Mamykina Lena. No Longer Wearing: Investigating the Abandonment of Personal Health-tracking Technologies on Craigslist. UbiComp. 2015:647–658. [Google Scholar]
11. Collins Francis S, Varmus Harold. A new initiative on precision medicine. New England Journal of Medicine. 2015;372(9):793–795. 2015. [PMC free article] [PubMed] [Google Scholar]
12. Consolvo Sunny, Everitt Katherine, Smith Ian, Landay James A. Design requirements for technologies that encourage physical activity. CHI. 2006:457–466. [Google Scholar]
13. Consolvo Sunny, Klasnja Predrag, McDonald David W, Landay James A. Proceedings of the 4th international Conference on Persuasive Technology. ACM; 2009. Goal-setting considerations for persuasive technologies that encourage physical activity; p. 8. [Google Scholar]
14. Cordeiro Felicia, Epstein Daniel A, Thomaz Edison, Bales Elizabeth, Jagannathan Arvind K, Abowd Gregory D, Fogarty James. Barriers and Negative Nudges: Exploring Challenges in Food Journaling. CHI. 2015:1159–1162. [PMC free article] [PubMed] [Google Scholar]
15. Culotta Aron. Estimating county health statistics with Twitter. CHI. 2014:1335–1344. [Google Scholar]
16. De Choudhury Munmun, Counts Scott, Horvitz Eric, Hoff Aaron. Characterizing and Predicting Postpartum Depression from Facebook Data. CSCW. 2014:626–638. [Google Scholar]
17. De Choudhury Munmun, Gamon Michael, Counts Scott, Horvitz Eric. Predicting depression via social media. ICWSM 2013 [Google Scholar]
18. De Choudhury Munmun, Kiciman Emre, Dredze Mark, Coppersmith Glen, Kumar Mrinal. Discovering Shifts to Suicidal Ideation from Mental Health Content in Social Media. CHI. 2016:2098–2110. [PMC free article] [PubMed] [Google Scholar]
19. Dickey David A, Fuller Wayne A. Likelihood ratio statistics for autoregressive time series with a unit root. Econometrica: Journal of the Econometric Society. 1981;(1981):1057–1072. [Google Scholar]
20. Estrin Deborah. Small data, where n= me. Commun. ACM. 2014;57(4):32–34. 2014. [Google Scholar]
21. Eysenbach Gunther, Powell John, Englesakis Marina, Rizo Carlos, Stern Anita. Health related virtual communities and electronic support groups: systematic review of the effects of online peer to peer interactions. Bmj. 2004;328(7449):1166. 2004. [PMC free article] [PubMed] [Google Scholar]
22. Finer Nicholas. Predicting therapeutic weight loss. American Journal of Clinical Nutrition. 2015;101(3):419–420. 2015. [PMC free article] [PubMed] [Google Scholar]
23. Garimella Venkata Rama Kiran, Alfayad Abdulrahman, Weber Ingmar. Social Media Image Analysis for Public Health. Conference on Human Factors in Computing Systems (CHI) :5543–5547. [Google Scholar]
24. Geweke John F. Measures of conditional linear dependence and feedback between time series. J. Amer. Statist. Assoc. 1984;79(388):907–915. 1984. [Google Scholar]
25. Goebel Rainer, Roebroeck Alard, Kim Dae-Shik, Formisano Elia. Investigating directed cortical interactions in time-resolved fMRI data using vector autoregressive modeling and Granger causality mapping. Magnetic resonance imaging. 2003;21(10):1251–1261. 2003. [PubMed] [Google Scholar]
26. Haddadi Hamed, Ofli Ferda, Mejova Yelena, Weber Ingmar, Srivastava Jaideep. International Conference on Healthcare Informatics (ICHI) IEEE; 2015. 360-degree Quantified Self; pp. 587–592. [Google Scholar]
27. Huh Jina, Ackerman Mark S. Collaborative Help in Chronic Disease Management: Supporting Individualized Problems. CSCW 2012 [PMC free article] [PubMed] [Google Scholar]
28. Ivanov Anton, Sharman Raj, Rao HRaghav. Exploring factors impacting sharing health-tracking records. Health Policy and Technology. 2015;4(Issue 3):263–276. 2015. [Google Scholar]
29. Johnson Grace J, Ambrose Paul J. Neo-tribes: The power and potential of online communities in health care. Commun. ACM. 2006;49(1):107–113. 2006. [Google Scholar]
30. Kocielnik Rafal, Sidorova Natalia, Maggi Fabrizio M, Ouwerkerk Martin, Westerink Joyce HDM. Smart technologies for long-term stress monitoring at work. Computer-Based Medical Systems (CBMS) 2013:53–58. [Google Scholar]31. Kostkova Patty. Public Health. In: Mejova Yelena, Weber Ingmar, Macy Michael., editors. Twitter: A Digital Socioscope. Cambridge University Press; 2015. pp. 111–130. [Google Scholar]
32. Lu Hong, Frauendorfer Denise, Rabbi Mashfiqui, Mast Marianne Schmid, Chittaranjan Gokul T, Campbell Andrew T, Gatica-Perez Daniel, Choudhury Tanzeem. Stresssense: Detecting stress in unconstrained acoustic environments using smartphones. Conference on Ubiquitous Computing (UbiComp) 2012:351–360. [Google Scholar]
33. Mamykina Lena, Nakikj Drashko, Elhadad Noemie. Collective Sensemaking in Online Health Forums. CHI. 2015:3217–3226. [Google Scholar]
34. Mankoff Jennifer, Kuksenok Kateryna, Kiesler Sara, Rode Jennifer A, Waldman Kelly. Competing online viewpoints and models of chronic illness. CHI. 2011:589–598. [Google Scholar]
35. Mejova Yelena, Abbar Sofiane, Haddadi Hamed. Fetishizing Food in Digital Age:# foodporn Around the World. ICWSM 2016 [Google Scholar]
36. Meyer Jochen, Simske Steven, Siek Katie A, Gurrin Cathal G, Hermens Hermie. Beyond Quantified Self: Data for Wellbeing. CHI. 2014:95–98. [Google Scholar]
37. Munson Sean A, Consolvo Sunny. Exploring goal-setting, rewards, self-monitoring, and sharing to motivate physical activity. Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) 2012:25–32. [Google Scholar]
38. Murnane Elizabeth L, Counts Scott. Unraveling Abstinence and Relapse: Smoking Cessation Reflected in Social Media. CHI. 2014:1345–1354. [Google Scholar]
39. Murnane Elizabeth L, Huffaker David, Kossinets Gueorgi. Mobile health apps: adoption, adherence, and abandonment. Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) 2015:261–264. [Google Scholar]
40. Newman Mark W, Lauterbach Debra, Munson Sean A, Resnick Paul, Morris Margaret E. It’s not that I don’t have problems, I’m just not putting them on Facebook: challenges and opportunities in using online social networks for health. CSCW. 2011:341–350. [Google Scholar]
41. Otter Pieter W. On Wiener-Granger causality, information and canonical correlation. Economics Letters. 1991;35(2):187–191. 1991. [Google Scholar]
42. Padrez Kevin A, Ungar Lyle, Schwartz Hansen Andrew, Smith Robert J, Hill Shawndra, Antanavicius Tadas, Brown Dana M, Crutchley Patrick, Asch David A, Merchant Raina M. Linking social media and medical record data: a study of adults presenting to an academic, urban emergency department. BMJ quality & safety. 2015 (2015), bmjqs–2015. [PubMed] [Google Scholar]
43. Park Kunwoo, Weber Ingmar, Cha Meeyoung, Lee Chul. Persistent sharing of fitness app status on twitter. CSCW 2016 [Google Scholar]
44. Paul Michael J, Dredze Mark. You Are What You Tweet: Analyzing Twitter for Public Health. ICWSM 2011 [Google Scholar]
45. Ritz Patrick, Caiazzo Robert, Becouarn Guillaume, Arnalsteen Laurent, Andrieu Sandrine, Topart Philippe, Pattou Franois. Early prediction of failure to lose weight after obesity surgery. Surgery for Obesity and Related Diseases. 2013;9(Issue 1):118–121. 2013. [PubMed] [Google Scholar]46. Sallis James F, Owen Neville, Fisher Edwin B. Ecological models of health behavior. Health behavior and health education: Theory, research, and practice. 2008;4(2008):465–486. [Google Scholar]47. Schwarzer Ralf. Modeling health behavior change: How to predict and modify the adoption and maintenance of health behaviors. Applied Psychology. 2008;57(1):1–29. 2008. [Google Scholar]
48. Shapiro Samuel S, Wilk Martin B, Chen Hwei J. A comparative study of various tests for normality. J. Amer. Statist. Assoc. 1968;63(324):1343–1372. 1968. [Google Scholar]
49. Strecher Victor J, DeVellis Brenda McEvoy, Becker Marshall H, Rosenstock Irwin M. The role of self-efficacy in achieving health behavior change. Health Education & behavior. 1986;13(1):73–92. 1986. [PubMed] [Google Scholar]
50. Strecher Victor J, Seijts Gerard H, Kok Gerjo J, Latham Gary P, Glasgow Russell, DeVellis Brenda, Meertens Ree M, Bulger David W. Goal setting as a strategy for health behavior change. Health Education & behavior. 1995;22(2):190–200. 1995. [PubMed] [Google Scholar]
51. Teodoro Rannie, Mor Naaman. Fitter with Twitter: Understanding Personal Health and Fitness Activity in Social Media. ICWSM. 2013:611–620. [Google Scholar]
52. Thomas Diana M, Ivanescu Andrada E, Martin Corby K, Heymsfield Steven B, Marshall Kaitlyn, Bodrato Victoria E, Williamson Donald A, Anton Stephen D, Sacks Frank M, Ryan Donna, Bray George A. Predicting successful long-term weight loss from short-term weight-loss outcomes: new insights from a dynamic energy balance model (the POUNDS Lost study) American Journal of Clinical Nutrition. 2015;101(3):449–454. 2015. [PMC free article] [PubMed] [Google Scholar]
53. Vickey Theodore A, Breslin John G. A Study on Twitter Usage for Fitness Self-Reporting via Mobile Apps. AAAI Spring Symposium: Self-Tracking and Collective Intelligence for Personal Wellness. 2012:65–70. [Google Scholar]
54. Wagner Claudia, Singer Philipp, Strohmaier Markus. Spatial and Temporal Patterns of Online Food Preferences; World Wide Web Conference (WWW); 2014. pp. 553–554. [Google Scholar]
55. Wang Rui, Chen Fanglin, Chen Zhenyu, Li Tianxing, Harari Gabriella, Tignor Stefanie, Zhou Xia, Ben-Zeev Dror, Campbell Andrew T. StudentLife: assessing mental health, academic performance and behavioral trends of college students using smartphones. Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) 2014:3–14. [Google Scholar]
56. Wang Yafei, Weber Ingmar, Mitra Prasenjit. Quantified Self Meets Social Media: Sharing of Weight Updates on Twitter. ACM Digital Health (DH) 2016:93–97. [Google Scholar]
57. Weber Ingmar, Achananuparp Palakorn. Insights from machine-learned diet success prediction. Pacific Symposium on Biocomputing (PSB) 2016:540–551. [PubMed] [Google Scholar]
58. Weber Ingmar, Mejova Yelena. Crowdsourcing Health Labels: Inferring Body Weight from Profile Pictures. ACM Digital Health (DH) 2016:105–109. [Google Scholar]
59. Whitson Jennifer R. Gaming the quantified self. Surveillance & Society. 2013;11(1/2):163. 2013. [Google Scholar]
60. Ye Xu, Chen Guanling, Gao Yang, Wang Honghao, Cao Yu. Assisting Food Journaling with Automatic Eating Detection. CHI. 2016:3255–3262. [Google Scholar]