Crowdsourcing health labels

Inferring body weight from profile pictures

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

8 Citations (Scopus)

Abstract

To use social media for health-related analysis, one key step is the detection of health-related labels for users. But unlike transient conditions like u, social media users are less vocal about chronic conditions such as obesity, as users might not tweet \I'm still overweight". As, however, obesity-related conditions such as diabetes, heart disease, osteoarthritis, and even cancer are on the rise, this obese-or-not label could be one of the most useful for studies in public health. In this paper we investigate the feasibility of using profile pictures to infer if a user is overweight or not. We show that this is indeed possible and further show that the fraction of labeled-As-overweight users is higher in U.S. counties with higher obesity rates. Going from public to individual health analysis, we then find differences both in behavior and social networks, for example finding users labeled as overweight to have fewer followers.

Original languageEnglish
Title of host publicationDH 2016 - Proceedings of the 2016 Digital Health Conference
PublisherAssociation for Computing Machinery, Inc
Pages105-109
Number of pages5
ISBN (Print)9781450342247
DOIs
Publication statusPublished - 11 Apr 2016
Event6th International Conference on Digital Health, DH 2016 - Montreal, Canada
Duration: 11 Apr 201613 Apr 2016

Other

Other6th International Conference on Digital Health, DH 2016
CountryCanada
CityMontreal
Period11/4/1613/4/16

Fingerprint

Crowdsourcing
Labels
Body Weight
Health
Social Media
Obesity
Public health
Medical problems
Social Support
Osteoarthritis
Heart Diseases
Public Health
Neoplasms

Keywords

  • BMI
  • Obesity
  • Profile Images
  • Social Network Analysis
  • Twitter

ASJC Scopus subject areas

  • Health Information Management
  • Computer Science Applications
  • Health Informatics

Cite this

Weber, I., & Mejova, Y. (2016). Crowdsourcing health labels: Inferring body weight from profile pictures. In DH 2016 - Proceedings of the 2016 Digital Health Conference (pp. 105-109). Association for Computing Machinery, Inc. https://doi.org/10.1145/2896338.2896343

Crowdsourcing health labels : Inferring body weight from profile pictures. / Weber, Ingmar; Mejova, Yelena.

DH 2016 - Proceedings of the 2016 Digital Health Conference. Association for Computing Machinery, Inc, 2016. p. 105-109.

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

Weber, I & Mejova, Y 2016, Crowdsourcing health labels: Inferring body weight from profile pictures. in DH 2016 - Proceedings of the 2016 Digital Health Conference. Association for Computing Machinery, Inc, pp. 105-109, 6th International Conference on Digital Health, DH 2016, Montreal, Canada, 11/4/16. https://doi.org/10.1145/2896338.2896343
Weber I, Mejova Y. Crowdsourcing health labels: Inferring body weight from profile pictures. In DH 2016 - Proceedings of the 2016 Digital Health Conference. Association for Computing Machinery, Inc. 2016. p. 105-109 https://doi.org/10.1145/2896338.2896343
Weber, Ingmar ; Mejova, Yelena. / Crowdsourcing health labels : Inferring body weight from profile pictures. DH 2016 - Proceedings of the 2016 Digital Health Conference. Association for Computing Machinery, Inc, 2016. pp. 105-109
@inproceedings{a4a977e9cead44098e6d2ffb8727e048,
title = "Crowdsourcing health labels: Inferring body weight from profile pictures",
abstract = "To use social media for health-related analysis, one key step is the detection of health-related labels for users. But unlike transient conditions like u, social media users are less vocal about chronic conditions such as obesity, as users might not tweet \I'm still overweight{"}. As, however, obesity-related conditions such as diabetes, heart disease, osteoarthritis, and even cancer are on the rise, this obese-or-not label could be one of the most useful for studies in public health. In this paper we investigate the feasibility of using profile pictures to infer if a user is overweight or not. We show that this is indeed possible and further show that the fraction of labeled-As-overweight users is higher in U.S. counties with higher obesity rates. Going from public to individual health analysis, we then find differences both in behavior and social networks, for example finding users labeled as overweight to have fewer followers.",
keywords = "BMI, Obesity, Profile Images, Social Network Analysis, Twitter",
author = "Ingmar Weber and Yelena Mejova",
year = "2016",
month = "4",
day = "11",
doi = "10.1145/2896338.2896343",
language = "English",
isbn = "9781450342247",
pages = "105--109",
booktitle = "DH 2016 - Proceedings of the 2016 Digital Health Conference",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Crowdsourcing health labels

T2 - Inferring body weight from profile pictures

AU - Weber, Ingmar

AU - Mejova, Yelena

PY - 2016/4/11

Y1 - 2016/4/11

N2 - To use social media for health-related analysis, one key step is the detection of health-related labels for users. But unlike transient conditions like u, social media users are less vocal about chronic conditions such as obesity, as users might not tweet \I'm still overweight". As, however, obesity-related conditions such as diabetes, heart disease, osteoarthritis, and even cancer are on the rise, this obese-or-not label could be one of the most useful for studies in public health. In this paper we investigate the feasibility of using profile pictures to infer if a user is overweight or not. We show that this is indeed possible and further show that the fraction of labeled-As-overweight users is higher in U.S. counties with higher obesity rates. Going from public to individual health analysis, we then find differences both in behavior and social networks, for example finding users labeled as overweight to have fewer followers.

AB - To use social media for health-related analysis, one key step is the detection of health-related labels for users. But unlike transient conditions like u, social media users are less vocal about chronic conditions such as obesity, as users might not tweet \I'm still overweight". As, however, obesity-related conditions such as diabetes, heart disease, osteoarthritis, and even cancer are on the rise, this obese-or-not label could be one of the most useful for studies in public health. In this paper we investigate the feasibility of using profile pictures to infer if a user is overweight or not. We show that this is indeed possible and further show that the fraction of labeled-As-overweight users is higher in U.S. counties with higher obesity rates. Going from public to individual health analysis, we then find differences both in behavior and social networks, for example finding users labeled as overweight to have fewer followers.

KW - BMI

KW - Obesity

KW - Profile Images

KW - Social Network Analysis

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84966657898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966657898&partnerID=8YFLogxK

U2 - 10.1145/2896338.2896343

DO - 10.1145/2896338.2896343

M3 - Conference contribution

SN - 9781450342247

SP - 105

EP - 109

BT - DH 2016 - Proceedings of the 2016 Digital Health Conference

PB - Association for Computing Machinery, Inc

ER -