The pictures we like are our image: continuous mapping of favorite pictures into self-assessed and attributed personality traits
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-01082
- Type
- D - Journal article
- DOI
-
10.1109/TAFFC.2016.2516994
- Title of journal
- IEEE Transactions on Affective Computing
- Article number
- -
- First page
- 268
- Volume
- 8
- Issue
- 2
- ISSN
- 1949-3045
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- Year of publication
- 2017
- URL
-
http://eprints.gla.ac.uk/124063/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 23
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: First automatic method to infer personality traits and identify visual properties which convey desirable personality impressions from pictures posted on social media. First work to show that posted pictures act as social signals. RIGOUR: Method used novel Topic Models, built using 60,000 images from 300 users assessed by 12 experts in terms of Big 5 personality traits. SIGNIFICANCE: published in top IEEE journal. Work builds on a previous ACM Multimedia paper (https://dl.acm.org/doi/10.1145/2502081.2502280) recognized as a prestigious “Brave New Idea” contribution (https://2020.acmmm.org/bni-proposals.html). The two student co-authors were hired by Microsoft Research and Netflix Research based on the work.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
