Computational approaches toward integrating quantified self sensing and social media

Munmun De Choudhury, Mrinal Kumar, Ingmar Weber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationCSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing
PublisherAssociation for Computing Machinery
Pages1334-1349
Number of pages16
ISBN (Electronic)9781450343350
DOIs
Publication statusPublished - 25 Feb 2017
Event2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW 2017 - Portland, United States
Duration: 25 Feb 20171 Mar 2017

Other

Other2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW 2017
CountryUnited States
CityPortland
Period25/2/171/3/17

Fingerprint

Nutrition
Health
Bioelectric potentials
Linguistics
Medicine
Compliance

Keywords

  • Behavior change
  • Diet
  • Fitness
  • Health
  • MyFitnessPal
  • Quantified self
  • Social media
  • Twitter
  • Well-being

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

De Choudhury, M., Kumar, M., & Weber, I. (2017). Computational approaches toward integrating quantified self sensing and social media. In CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing (pp. 1334-1349). Association for Computing Machinery. https://doi.org/10.1145/2998181.2998219

Computational approaches toward integrating quantified self sensing and social media. / De Choudhury, Munmun; Kumar, Mrinal; Weber, Ingmar.

CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery, 2017. p. 1334-1349.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

De Choudhury, M, Kumar, M & Weber, I 2017, Computational approaches toward integrating quantified self sensing and social media. in CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery, pp. 1334-1349, 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW 2017, Portland, United States, 25/2/17. https://doi.org/10.1145/2998181.2998219
De Choudhury M, Kumar M, Weber I. Computational approaches toward integrating quantified self sensing and social media. In CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery. 2017. p. 1334-1349 https://doi.org/10.1145/2998181.2998219
De Choudhury, Munmun ; Kumar, Mrinal ; Weber, Ingmar. / Computational approaches toward integrating quantified self sensing and social media. CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery, 2017. pp. 1334-1349
@inproceedings{e2fd63f69d424281aad795a6da6c67c3,
title = "Computational approaches toward integrating quantified self sensing and social media",
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.",
keywords = "Behavior change, Diet, Fitness, Health, MyFitnessPal, Quantified self, Social media, Twitter, Well-being",
author = "{De Choudhury}, Munmun and Mrinal Kumar and Ingmar Weber",
year = "2017",
month = "2",
day = "25",
doi = "10.1145/2998181.2998219",
language = "English",
pages = "1334--1349",
booktitle = "CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Computational approaches toward integrating quantified self sensing and social media

AU - De Choudhury, Munmun

AU - Kumar, Mrinal

AU - Weber, Ingmar

PY - 2017/2/25

Y1 - 2017/2/25

N2 - 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.

AB - 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.

KW - Behavior change

KW - Diet

KW - Fitness

KW - Health

KW - MyFitnessPal

KW - Quantified self

KW - Social media

KW - Twitter

KW - Well-being

UR - http://www.scopus.com/inward/record.url?scp=85014774735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014774735&partnerID=8YFLogxK

U2 - 10.1145/2998181.2998219

DO - 10.1145/2998181.2998219

M3 - Conference contribution

AN - SCOPUS:85014774735

SP - 1334

EP - 1349

BT - CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing

PB - Association for Computing Machinery

ER -