Is Saki #delicious?
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 pers...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM Press
2019
|
| Online Access: | https://hdl.handle.net/1721.1/122046 |
| _version_ | 1811081715492323328 |
|---|---|
| author | Ofli, Ferda Aytar, Yusuf Weber, Ingmar al Hammouri, Raggi Torralba, Antonio |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Ofli, Ferda Aytar, Yusuf Weber, Ingmar al Hammouri, Raggi Torralba, Antonio |
| author_sort | Ofli, Ferda |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T11:51:20Z |
| format | Article |
| id | mit-1721.1/122046 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:51:20Z |
| publishDate | 2019 |
| publisher | ACM Press |
| record_format | dspace |
| spelling | mit-1721.1/1220462022-10-01T06:29:42Z Is Saki #delicious? 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 Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory 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. 2019-09-10T18:44:13Z 2019-09-10T18:44:13Z 2017-04 2019-07-11T16:33:13Z Article http://purl.org/eprint/type/ConferencePaper 9781450349130 https://hdl.handle.net/1721.1/122046 Ofli, Ferda et al. "Is Saki #delicious?: The Food Perception Gap on Instagram and Its Relation to Health." Proceedings of the 26th International Conference on World Wide Web, April 2017, Perth, Australia, International World Wide Web Conference Committee, April 2017 © 2017 International World Wide Web Conference Committee (IW3C2) en http://dx.doi.org/10.1145/3038912.3052663 Proceedings of the 26th International Conference on World Wide Web Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf ACM Press ACM |
| spellingShingle | Ofli, Ferda Aytar, Yusuf Weber, Ingmar al Hammouri, Raggi Torralba, Antonio Is Saki #delicious? |
| title | Is Saki #delicious? |
| title_full | Is Saki #delicious? |
| title_fullStr | Is Saki #delicious? |
| title_full_unstemmed | Is Saki #delicious? |
| title_short | Is Saki #delicious? |
| title_sort | is saki delicious |
| url | https://hdl.handle.net/1721.1/122046 |
| work_keys_str_mv | AT ofliferda issakidelicious AT aytaryusuf issakidelicious AT weberingmar issakidelicious AT alhammouriraggi issakidelicious AT torralbaantonio issakidelicious AT ofliferda issakideliciousthefoodperceptiongaponinstagramanditsrelationtohealth AT aytaryusuf issakideliciousthefoodperceptiongaponinstagramanditsrelationtohealth AT weberingmar issakideliciousthefoodperceptiongaponinstagramanditsrelationtohealth AT alhammouriraggi issakideliciousthefoodperceptiongaponinstagramanditsrelationtohealth AT torralbaantonio issakideliciousthefoodperceptiongaponinstagramanditsrelationtohealth |