Using geolocated Twitter data to monitor the prevalence of healthy and unhealthy food references across the US

Michael J. Widener, WenWen Li

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

Mining the social media outlet Twitter for geolocated messages provides a rich database of information on people's thoughts and sentiments about myriad topics, like public health. Examining this spatial data has been particularly useful to researchers interested in monitoring and mapping disease outbreaks, like influenza. However, very little has been done to utilize this massive resource to examine other public health issues. This paper uses an advanced data-mining framework with a novel use of social media data retrieval and sentiment analysis to understand how geolocated tweets can be used to explore the prevalence of healthy and unhealthy food across the contiguous United States. Additionally, tweets are associated with spatial data provided by the US Department of Agriculture (USDA) of low-income, low-access census tracts (e.g. food deserts), to examine whether tweets about unhealthy foods are more common in these disadvantaged areas. Results show that these disadvantaged census tracts tend to have both a lower proportion of tweets about healthy foods with a positive sentiment, and a higher proportion of unhealthy tweets in general. These findings substantiate the methods used by the USDA to identify regions that are at risk of having low access to healthy foods.

Original languageEnglish (US)
Pages (from-to)189-197
Number of pages9
JournalApplied Geography
Volume54
DOIs
StatePublished - 2014

Fingerprint

social networks
twitter
spatial data
USDA
public health
food
monitoring
influenza
income
social media
researchers
census
agriculture
data mining
desert
contagious disease
low income
Twitter
Food
Disease

Keywords

  • Food deserts
  • Nutrition
  • Public health
  • Spatial analysis
  • Twitter

ASJC Scopus subject areas

  • Forestry
  • Tourism, Leisure and Hospitality Management
  • Environmental Science(all)
  • Geography, Planning and Development

Cite this

Using geolocated Twitter data to monitor the prevalence of healthy and unhealthy food references across the US. / Widener, Michael J.; Li, WenWen.

In: Applied Geography, Vol. 54, 2014, p. 189-197.

Research output: Contribution to journalArticle

@article{90da78330b38449ba951a01c49bca510,
title = "Using geolocated Twitter data to monitor the prevalence of healthy and unhealthy food references across the US",
abstract = "Mining the social media outlet Twitter for geolocated messages provides a rich database of information on people's thoughts and sentiments about myriad topics, like public health. Examining this spatial data has been particularly useful to researchers interested in monitoring and mapping disease outbreaks, like influenza. However, very little has been done to utilize this massive resource to examine other public health issues. This paper uses an advanced data-mining framework with a novel use of social media data retrieval and sentiment analysis to understand how geolocated tweets can be used to explore the prevalence of healthy and unhealthy food across the contiguous United States. Additionally, tweets are associated with spatial data provided by the US Department of Agriculture (USDA) of low-income, low-access census tracts (e.g. food deserts), to examine whether tweets about unhealthy foods are more common in these disadvantaged areas. Results show that these disadvantaged census tracts tend to have both a lower proportion of tweets about healthy foods with a positive sentiment, and a higher proportion of unhealthy tweets in general. These findings substantiate the methods used by the USDA to identify regions that are at risk of having low access to healthy foods.",
keywords = "Food deserts, Nutrition, Public health, Spatial analysis, Twitter",
author = "Widener, {Michael J.} and WenWen Li",
year = "2014",
doi = "10.1016/j.apgeog.2014.07.017",
language = "English (US)",
volume = "54",
pages = "189--197",
journal = "Applied Geography",
issn = "0143-6228",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Using geolocated Twitter data to monitor the prevalence of healthy and unhealthy food references across the US

AU - Widener, Michael J.

AU - Li, WenWen

PY - 2014

Y1 - 2014

N2 - Mining the social media outlet Twitter for geolocated messages provides a rich database of information on people's thoughts and sentiments about myriad topics, like public health. Examining this spatial data has been particularly useful to researchers interested in monitoring and mapping disease outbreaks, like influenza. However, very little has been done to utilize this massive resource to examine other public health issues. This paper uses an advanced data-mining framework with a novel use of social media data retrieval and sentiment analysis to understand how geolocated tweets can be used to explore the prevalence of healthy and unhealthy food across the contiguous United States. Additionally, tweets are associated with spatial data provided by the US Department of Agriculture (USDA) of low-income, low-access census tracts (e.g. food deserts), to examine whether tweets about unhealthy foods are more common in these disadvantaged areas. Results show that these disadvantaged census tracts tend to have both a lower proportion of tweets about healthy foods with a positive sentiment, and a higher proportion of unhealthy tweets in general. These findings substantiate the methods used by the USDA to identify regions that are at risk of having low access to healthy foods.

AB - Mining the social media outlet Twitter for geolocated messages provides a rich database of information on people's thoughts and sentiments about myriad topics, like public health. Examining this spatial data has been particularly useful to researchers interested in monitoring and mapping disease outbreaks, like influenza. However, very little has been done to utilize this massive resource to examine other public health issues. This paper uses an advanced data-mining framework with a novel use of social media data retrieval and sentiment analysis to understand how geolocated tweets can be used to explore the prevalence of healthy and unhealthy food across the contiguous United States. Additionally, tweets are associated with spatial data provided by the US Department of Agriculture (USDA) of low-income, low-access census tracts (e.g. food deserts), to examine whether tweets about unhealthy foods are more common in these disadvantaged areas. Results show that these disadvantaged census tracts tend to have both a lower proportion of tweets about healthy foods with a positive sentiment, and a higher proportion of unhealthy tweets in general. These findings substantiate the methods used by the USDA to identify regions that are at risk of having low access to healthy foods.

KW - Food deserts

KW - Nutrition

KW - Public health

KW - Spatial analysis

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84906860144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906860144&partnerID=8YFLogxK

U2 - 10.1016/j.apgeog.2014.07.017

DO - 10.1016/j.apgeog.2014.07.017

M3 - Article

AN - SCOPUS:84906860144

VL - 54

SP - 189

EP - 197

JO - Applied Geography

JF - Applied Geography

SN - 0143-6228

ER -