Analyzing Connections Between User Attributes, Images, and Text

Burdick, Laura and Mihalcea, Rada and Boyd, Ryan and Pennebaker, James W. (2020) Analyzing Connections Between User Attributes, Images, and Text. Cognitive Computation. ISSN 1866-9956

[img]
Text (Accepted Draft)
Accepted_Draft.pdf - Accepted Version
Restricted to Repository staff only until 13 February 2021.
Available under License Creative Commons Attribution-NonCommercial.

Download (31MB)

Abstract

This work explores the relationship between a person’s demographic/ psychological traits (e.g., gender, personality) and selfidentity images and captions. We use a dataset of images and captions provided by N = 1,350 individuals, and we automatically extract features from both the images and captions. We identify several visual and textual properties that show reliable relationships with individual differences between participants. The automated techniques presented here allow us to draw interesting conclusions from our data that would be difficult to identify manually, and these techniques are extensible to other large datasets. We believe that our work on the relationship between user characteristics and user data has relevance in online settings, where users upload billions of images each day (Meeker M, 2014. Internet trends 2014–Code conference. Retrieved May 28, 2014).

Item Type:
Journal Article
Journal or Publication Title:
Cognitive Computation
Additional Information:
The final publication is available at Springer via https://link.springer.com/article/10.1007/s12559-019-09695-3
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1707
Subjects:
ID Code:
138296
Deposited By:
Deposited On:
31 Oct 2019 13:50
Refereed?:
Yes
Published?:
Published
Last Modified:
30 Mar 2020 10:36