Is Saki #delicious? The food perception gap on instagram and its relation to health

Ferda Ofli, Yusuf Aytar, Ingmar Weber, Raggi Al Hammouri, Antonio Torralba

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

14 Citations (Scopus)

Abstract

Food is an integral part of our life and what and how much we eat crucially affects our health. Our food choices largely depend on how we perceive certain characteristics of food, such as whether it is healthy, delicious or if it qualifies as a salad. But these perceptions differ from person to person and one person’s “single lettuce leaf” might be another person’s “side salad”. Studying how food is perceived in relation to what it actually is typically involves a laboratory setup. Here we propose to use recent advances in image recognition to tackle this problem. Concretely, we use data for 1.9 million images from Instagram from the US to look at systematic differences in how a machine would objectively label an image compared to how a human subjectively does. We show that this difference, which we call the “perception gap”, relates to a number of health outcomes observed at the county level. To the best of our knowledge, this is the first time that image recognition is being used to study the “misalignment” of how people describe food images vs. what they actually depict.

Original languageEnglish
Title of host publication26th International World Wide Web Conference, WWW 2017
PublisherInternational World Wide Web Conferences Steering Committee
Pages509-518
Number of pages10
ISBN (Print)9781450349147
DOIs
Publication statusPublished - 1 Jan 2017
Event26th International World Wide Web Conference, WWW 2017 - Perth, Australia
Duration: 3 Apr 20177 Apr 2017

Other

Other26th International World Wide Web Conference, WWW 2017
CountryAustralia
CityPerth
Period3/4/177/4/17

Fingerprint

Health
Image recognition
Labels

Keywords

  • Computer vision
  • Food
  • Instagram
  • Public health

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications

Cite this

Ofli, F., Aytar, Y., Weber, I., Al Hammouri, R., & Torralba, A. (2017). Is Saki #delicious? The food perception gap on instagram and its relation to health. In 26th International World Wide Web Conference, WWW 2017 (pp. 509-518). [3052663] International World Wide Web Conferences Steering Committee. https://doi.org/10.1145/3038912.3052663

Is Saki #delicious? The food perception gap on instagram and its relation to health. / Ofli, Ferda; Aytar, Yusuf; Weber, Ingmar; Al Hammouri, Raggi; Torralba, Antonio.

26th International World Wide Web Conference, WWW 2017. International World Wide Web Conferences Steering Committee, 2017. p. 509-518 3052663.

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

Ofli, F, Aytar, Y, Weber, I, Al Hammouri, R & Torralba, A 2017, Is Saki #delicious? The food perception gap on instagram and its relation to health. in 26th International World Wide Web Conference, WWW 2017., 3052663, International World Wide Web Conferences Steering Committee, pp. 509-518, 26th International World Wide Web Conference, WWW 2017, Perth, Australia, 3/4/17. https://doi.org/10.1145/3038912.3052663
Ofli F, Aytar Y, Weber I, Al Hammouri R, Torralba A. Is Saki #delicious? The food perception gap on instagram and its relation to health. In 26th International World Wide Web Conference, WWW 2017. International World Wide Web Conferences Steering Committee. 2017. p. 509-518. 3052663 https://doi.org/10.1145/3038912.3052663
Ofli, Ferda ; Aytar, Yusuf ; Weber, Ingmar ; Al Hammouri, Raggi ; Torralba, Antonio. / Is Saki #delicious? The food perception gap on instagram and its relation to health. 26th International World Wide Web Conference, WWW 2017. International World Wide Web Conferences Steering Committee, 2017. pp. 509-518
@inproceedings{98d7ab30b09544648a889046e613ddb7,
title = "Is Saki #delicious? The food perception gap on instagram and its relation to health",
abstract = "Food is an integral part of our life and what and how much we eat crucially affects our health. Our food choices largely depend on how we perceive certain characteristics of food, such as whether it is healthy, delicious or if it qualifies as a salad. But these perceptions differ from person to person and one person’s “single lettuce leaf” might be another person’s “side salad”. Studying how food is perceived in relation to what it actually is typically involves a laboratory setup. Here we propose to use recent advances in image recognition to tackle this problem. Concretely, we use data for 1.9 million images from Instagram from the US to look at systematic differences in how a machine would objectively label an image compared to how a human subjectively does. We show that this difference, which we call the “perception gap”, relates to a number of health outcomes observed at the county level. To the best of our knowledge, this is the first time that image recognition is being used to study the “misalignment” of how people describe food images vs. what they actually depict.",
keywords = "Computer vision, Food, Instagram, Public health",
author = "Ferda Ofli and Yusuf Aytar and Ingmar Weber and {Al Hammouri}, Raggi and Antonio Torralba",
year = "2017",
month = "1",
day = "1",
doi = "10.1145/3038912.3052663",
language = "English",
isbn = "9781450349147",
pages = "509--518",
booktitle = "26th International World Wide Web Conference, WWW 2017",
publisher = "International World Wide Web Conferences Steering Committee",

}

TY - GEN

T1 - Is Saki #delicious? The food perception gap on instagram and its relation to health

AU - Ofli, Ferda

AU - Aytar, Yusuf

AU - Weber, Ingmar

AU - Al Hammouri, Raggi

AU - Torralba, Antonio

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Food is an integral part of our life and what and how much we eat crucially affects our health. Our food choices largely depend on how we perceive certain characteristics of food, such as whether it is healthy, delicious or if it qualifies as a salad. But these perceptions differ from person to person and one person’s “single lettuce leaf” might be another person’s “side salad”. Studying how food is perceived in relation to what it actually is typically involves a laboratory setup. Here we propose to use recent advances in image recognition to tackle this problem. Concretely, we use data for 1.9 million images from Instagram from the US to look at systematic differences in how a machine would objectively label an image compared to how a human subjectively does. We show that this difference, which we call the “perception gap”, relates to a number of health outcomes observed at the county level. To the best of our knowledge, this is the first time that image recognition is being used to study the “misalignment” of how people describe food images vs. what they actually depict.

AB - Food is an integral part of our life and what and how much we eat crucially affects our health. Our food choices largely depend on how we perceive certain characteristics of food, such as whether it is healthy, delicious or if it qualifies as a salad. But these perceptions differ from person to person and one person’s “single lettuce leaf” might be another person’s “side salad”. Studying how food is perceived in relation to what it actually is typically involves a laboratory setup. Here we propose to use recent advances in image recognition to tackle this problem. Concretely, we use data for 1.9 million images from Instagram from the US to look at systematic differences in how a machine would objectively label an image compared to how a human subjectively does. We show that this difference, which we call the “perception gap”, relates to a number of health outcomes observed at the county level. To the best of our knowledge, this is the first time that image recognition is being used to study the “misalignment” of how people describe food images vs. what they actually depict.

KW - Computer vision

KW - Food

KW - Instagram

KW - Public health

UR - http://www.scopus.com/inward/record.url?scp=85051470528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051470528&partnerID=8YFLogxK

U2 - 10.1145/3038912.3052663

DO - 10.1145/3038912.3052663

M3 - Conference contribution

SN - 9781450349147

SP - 509

EP - 518

BT - 26th International World Wide Web Conference, WWW 2017

PB - International World Wide Web Conferences Steering Committee

ER -