You tweet what you eat: Studying food consumption through twitter

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

87 Citations (Scopus)

Abstract

Food is an integral part of our lives, cultures, and wellbeing, 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 [10]. 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 [6]) by inducing two social networks using mentions and reciprocal following relationships.

Original languageEnglish
Title of host publicationConference on Human Factors in Computing Systems - Proceedings
PublisherAssociation for Computing Machinery
Pages3197-3206
Number of pages10
Volume2015-April
ISBN (Print)9781450331456
DOIs
Publication statusPublished - 18 Apr 2015
Event33rd Annual CHI Conference on Human Factors in Computing Systems, CHI 2015 - Seoul, Korea, Republic of
Duration: 18 Apr 201523 Apr 2015

Other

Other33rd Annual CHI Conference on Human Factors in Computing Systems, CHI 2015
CountryKorea, Republic of
CitySeoul
Period18/4/1523/4/15

Fingerprint

Education
Public health
Medical problems
Statistics
Economics

Keywords

  • Dietary health
  • Food
  • Obesity
  • Social networks
  • Twitter

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Abbar, S., Mejova, Y., & Weber, I. (2015). You tweet what you eat: Studying food consumption through twitter. In Conference on Human Factors in Computing Systems - Proceedings (Vol. 2015-April, pp. 3197-3206). Association for Computing Machinery. https://doi.org/10.1145/2702123.2702153

You tweet what you eat : Studying food consumption through twitter. / Abbar, Sofiane; Mejova, Yelena; Weber, Ingmar.

Conference on Human Factors in Computing Systems - Proceedings. Vol. 2015-April Association for Computing Machinery, 2015. p. 3197-3206.

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

Abbar, S, Mejova, Y & Weber, I 2015, You tweet what you eat: Studying food consumption through twitter. in Conference on Human Factors in Computing Systems - Proceedings. vol. 2015-April, Association for Computing Machinery, pp. 3197-3206, 33rd Annual CHI Conference on Human Factors in Computing Systems, CHI 2015, Seoul, Korea, Republic of, 18/4/15. https://doi.org/10.1145/2702123.2702153
Abbar S, Mejova Y, Weber I. You tweet what you eat: Studying food consumption through twitter. In Conference on Human Factors in Computing Systems - Proceedings. Vol. 2015-April. Association for Computing Machinery. 2015. p. 3197-3206 https://doi.org/10.1145/2702123.2702153
Abbar, Sofiane ; Mejova, Yelena ; Weber, Ingmar. / You tweet what you eat : Studying food consumption through twitter. Conference on Human Factors in Computing Systems - Proceedings. Vol. 2015-April Association for Computing Machinery, 2015. pp. 3197-3206
@inproceedings{57a0077860304e5dbd554619888e49ea,
title = "You tweet what you eat: Studying food consumption through twitter",
abstract = "Food is an integral part of our lives, cultures, and wellbeing, 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 [10]. 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 [6]) by inducing two social networks using mentions and reciprocal following relationships.",
keywords = "Dietary health, Food, Obesity, Social networks, Twitter",
author = "Sofiane Abbar and Yelena Mejova and Ingmar Weber",
year = "2015",
month = "4",
day = "18",
doi = "10.1145/2702123.2702153",
language = "English",
isbn = "9781450331456",
volume = "2015-April",
pages = "3197--3206",
booktitle = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - You tweet what you eat

T2 - Studying food consumption through twitter

AU - Abbar, Sofiane

AU - Mejova, Yelena

AU - Weber, Ingmar

PY - 2015/4/18

Y1 - 2015/4/18

N2 - Food is an integral part of our lives, cultures, and wellbeing, 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 [10]. 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 [6]) by inducing two social networks using mentions and reciprocal following relationships.

AB - Food is an integral part of our lives, cultures, and wellbeing, 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 [10]. 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 [6]) by inducing two social networks using mentions and reciprocal following relationships.

KW - Dietary health

KW - Food

KW - Obesity

KW - Social networks

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84951101871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951101871&partnerID=8YFLogxK

U2 - 10.1145/2702123.2702153

DO - 10.1145/2702123.2702153

M3 - Conference contribution

AN - SCOPUS:84951101871

SN - 9781450331456

VL - 2015-April

SP - 3197

EP - 3206

BT - Conference on Human Factors in Computing Systems - Proceedings

PB - Association for Computing Machinery

ER -