Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

FBAdLibrarian and Pykognition: open science tools for the collection and emotion detection of images in Facebook political ads with computer vision

Schmøkel, Rasmus and Bossetta, Michael LU (2022) In Journal of Information Technology & Politics 19(1). p.118-128
Abstract
We present a methodological workflow using two open science tools that we developed. The first, FBAdLibrian, collects images from the Facebook Ad Library. The second, Pykognition, simplifies facial and emotion detection in images using computer vision. We provide a methodological workflow for using these tools and apply them to a case study of the 2020 US primary elections. We find that unique images of campaigning candidates are only a fraction (<.1%) of overall ads. Furthermore, we find that candidates most often display happiness and calm in their facial displays, and they rarely attack opponents in image-based ads from their official Facebook pages. When candidates do attack, opponents are portrayed as displaying emotions such as... (More)
We present a methodological workflow using two open science tools that we developed. The first, FBAdLibrian, collects images from the Facebook Ad Library. The second, Pykognition, simplifies facial and emotion detection in images using computer vision. We provide a methodological workflow for using these tools and apply them to a case study of the 2020 US primary elections. We find that unique images of campaigning candidates are only a fraction (<.1%) of overall ads. Furthermore, we find that candidates most often display happiness and calm in their facial displays, and they rarely attack opponents in image-based ads from their official Facebook pages. When candidates do attack, opponents are portrayed as displaying emotions such as anger, sadness, and fear. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
computer vision, emotions, visual political communicaton, political communication, digital methods, computational social science, political campaigning
in
Journal of Information Technology & Politics
volume
19
issue
1
pages
118 - 128
publisher
Taylor & Francis
external identifiers
  • scopus:85107333959
ISSN
1933-1681
DOI
10.1080/19331681.2021.1928579
language
English
LU publication?
yes
id
71cab88c-5252-4036-a160-4efa509a6e9a
date added to LUP
2021-05-31 16:46:50
date last changed
2024-03-08 13:19:33
@article{71cab88c-5252-4036-a160-4efa509a6e9a,
  abstract     = {{We present a methodological workflow using two open science tools that we developed. The first, FBAdLibrian, collects images from the Facebook Ad Library. The second, Pykognition, simplifies facial and emotion detection in images using computer vision. We provide a methodological workflow for using these tools and apply them to a case study of the 2020 US primary elections. We find that unique images of campaigning candidates are only a fraction (&lt;.1%) of overall ads. Furthermore, we find that candidates most often display happiness and calm in their facial displays, and they rarely attack opponents in image-based ads from their official Facebook pages. When candidates do attack, opponents are portrayed as displaying emotions such as anger, sadness, and fear.}},
  author       = {{Schmøkel, Rasmus and Bossetta, Michael}},
  issn         = {{1933-1681}},
  keywords     = {{computer vision; emotions; visual political communicaton; political communication; digital methods; computational social science; political campaigning}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{118--128}},
  publisher    = {{Taylor & Francis}},
  series       = {{Journal of Information Technology & Politics}},
  title        = {{FBAdLibrarian and Pykognition: open science tools for the collection and emotion detection of images in Facebook political ads with computer vision}},
  url          = {{https://lup.lub.lu.se/search/files/98481312/FBAdLibrarian_and_Pykognition_open_science_tools_for_the_collection_and_emotion_detection_of_images_in_Facebook_political_ads_with_computer_vision.pdf}},
  doi          = {{10.1080/19331681.2021.1928579}},
  volume       = {{19}},
  year         = {{2022}},
}