Social media image analysis for public health

Venkata Rama Kiran, Abdulrahman Alfayad, Ingmar Weber

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

18 Citations (Scopus)

Abstract

Several projects have shown the feasibility to use textual social media data to track public health concerns, such as temporal influenza patterns or geographical obesity patterns. In this paper, we look at whether geo-tagged images from Instagram also provide a viable data source. Especially for "lifestyle" diseases, such as obesity, drinking or smoking, images of social gatherings could provide information that is not necessarily shared in, say, tweets. In this study, we explore whether (i) tags provided by the users and (ii) annotations obtained via automatic image tagging are indeed valuable for studying public health. We find that both user-provided and machine-generated tags provide information that can be used to infer a county's health statistics. Whereas for most statistics user-provided tags are better features, for predicting excessive drinking machine-generated tags such as "liquid" and "glass" yield better models. This hints at the potential of using machine-generated tags to study substance abuse.

Original languageEnglish
Title of host publicationCHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems
PublisherAssociation for Computing Machinery
Pages5543-5547
Number of pages5
ISBN (Electronic)9781450333627
DOIs
Publication statusPublished - 7 May 2016
Event34th Annual Conference on Human Factors in Computing Systems, CHI 2016 - San Jose, United States
Duration: 7 May 201612 May 2016

Other

Other34th Annual Conference on Human Factors in Computing Systems, CHI 2016
CountryUnited States
CitySan Jose
Period7/5/1612/5/16

Fingerprint

Public health
Image analysis
Statistics
Health
Glass
Liquids

ASJC Scopus subject areas

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

Cite this

Kiran, V. R., Alfayad, A., & Weber, I. (2016). Social media image analysis for public health. In CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems (pp. 5543-5547). Association for Computing Machinery. https://doi.org/10.1145/2858036.2858234

Social media image analysis for public health. / Kiran, Venkata Rama; Alfayad, Abdulrahman; Weber, Ingmar.

CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2016. p. 5543-5547.

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

Kiran, VR, Alfayad, A & Weber, I 2016, Social media image analysis for public health. in CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, pp. 5543-5547, 34th Annual Conference on Human Factors in Computing Systems, CHI 2016, San Jose, United States, 7/5/16. https://doi.org/10.1145/2858036.2858234
Kiran VR, Alfayad A, Weber I. Social media image analysis for public health. In CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. 2016. p. 5543-5547 https://doi.org/10.1145/2858036.2858234
Kiran, Venkata Rama ; Alfayad, Abdulrahman ; Weber, Ingmar. / Social media image analysis for public health. CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2016. pp. 5543-5547
@inproceedings{2d3e6e549ad34abd9f2e20252116b9e2,
title = "Social media image analysis for public health",
abstract = "Several projects have shown the feasibility to use textual social media data to track public health concerns, such as temporal influenza patterns or geographical obesity patterns. In this paper, we look at whether geo-tagged images from Instagram also provide a viable data source. Especially for {"}lifestyle{"} diseases, such as obesity, drinking or smoking, images of social gatherings could provide information that is not necessarily shared in, say, tweets. In this study, we explore whether (i) tags provided by the users and (ii) annotations obtained via automatic image tagging are indeed valuable for studying public health. We find that both user-provided and machine-generated tags provide information that can be used to infer a county's health statistics. Whereas for most statistics user-provided tags are better features, for predicting excessive drinking machine-generated tags such as {"}liquid{"} and {"}glass{"} yield better models. This hints at the potential of using machine-generated tags to study substance abuse.",
author = "Kiran, {Venkata Rama} and Abdulrahman Alfayad and Ingmar Weber",
year = "2016",
month = "5",
day = "7",
doi = "10.1145/2858036.2858234",
language = "English",
pages = "5543--5547",
booktitle = "CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Social media image analysis for public health

AU - Kiran, Venkata Rama

AU - Alfayad, Abdulrahman

AU - Weber, Ingmar

PY - 2016/5/7

Y1 - 2016/5/7

N2 - Several projects have shown the feasibility to use textual social media data to track public health concerns, such as temporal influenza patterns or geographical obesity patterns. In this paper, we look at whether geo-tagged images from Instagram also provide a viable data source. Especially for "lifestyle" diseases, such as obesity, drinking or smoking, images of social gatherings could provide information that is not necessarily shared in, say, tweets. In this study, we explore whether (i) tags provided by the users and (ii) annotations obtained via automatic image tagging are indeed valuable for studying public health. We find that both user-provided and machine-generated tags provide information that can be used to infer a county's health statistics. Whereas for most statistics user-provided tags are better features, for predicting excessive drinking machine-generated tags such as "liquid" and "glass" yield better models. This hints at the potential of using machine-generated tags to study substance abuse.

AB - Several projects have shown the feasibility to use textual social media data to track public health concerns, such as temporal influenza patterns or geographical obesity patterns. In this paper, we look at whether geo-tagged images from Instagram also provide a viable data source. Especially for "lifestyle" diseases, such as obesity, drinking or smoking, images of social gatherings could provide information that is not necessarily shared in, say, tweets. In this study, we explore whether (i) tags provided by the users and (ii) annotations obtained via automatic image tagging are indeed valuable for studying public health. We find that both user-provided and machine-generated tags provide information that can be used to infer a county's health statistics. Whereas for most statistics user-provided tags are better features, for predicting excessive drinking machine-generated tags such as "liquid" and "glass" yield better models. This hints at the potential of using machine-generated tags to study substance abuse.

UR - http://www.scopus.com/inward/record.url?scp=85014767368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014767368&partnerID=8YFLogxK

U2 - 10.1145/2858036.2858234

DO - 10.1145/2858036.2858234

M3 - Conference contribution

SP - 5543

EP - 5547

BT - CHI 2016 - Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

ER -