Conceptualizing depression in social media for the eventual protection of users against potential privacy invasions
Keywords
Loading...
Authors
Issue Date
2021-06-25
Language
en
Document type
Journal Title
Journal ISSN
Volume Title
Publisher
Title
ISSN
Volume
Issue
Startpage
Endpage
DOI
Abstract
Increasingly algorithms can infer sensitive information like depression using
public social media pro les. This work tries to address one of the biggest
challenges impeding the development of privacy protecting techniques in
regards to depression status, the lack of datasets that are ethically created.
Instead of using real pro les, this work explores the di erences between
depressed and not depressed users in social media images and based on
that creates a dataset that contains new pro les that are representative of
depressed or not depressed users. This way of creating new datasets could
be helpful in the future to help the development of new privacy protecting
techniques without impeding the privacy of users in the process.
Description
Citation
Supervisor
Faculty
Faculteit der Sociale Wetenschappen