Identifying Regional Trends in Avatar Customization

<p dir="ltr">Since virtual identities such as social media profiles and avatars have become a common venue for self-expression, it has become important to consider the ways in which existing systems embed the values of their designers. In order to design virtual identity systems that...

Full description

Saved in:
Bibliographic Details
Main Author: Peter Mawhorter (18602944) (author)
Other Authors: Sercan Sengun (18602947) (author), Haewoon Kwak (5747558) (author), D. Fox Harrell (18602950) (author)
Published: 2019
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513515134386176
author Peter Mawhorter (18602944)
author2 Sercan Sengun (18602947)
Haewoon Kwak (5747558)
D. Fox Harrell (18602950)
author2_role author
author
author
author_facet Peter Mawhorter (18602944)
Sercan Sengun (18602947)
Haewoon Kwak (5747558)
D. Fox Harrell (18602950)
author_role author
dc.creator.none.fl_str_mv Peter Mawhorter (18602944)
Sercan Sengun (18602947)
Haewoon Kwak (5747558)
D. Fox Harrell (18602950)
dc.date.none.fl_str_mv 2019-12-04T03:00:00Z
dc.identifier.none.fl_str_mv 10.1109/tg.2018.2835776
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Identifying_Regional_Trends_in_Avatar_Customization/25886920
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Human-centred computing
Avatars
Social network services
Games
Machine learning
Training
Market research
Prototypes
Artificial neural networks
clustering algorithms
cultural differences
data analysis
deep learning
image processing
unsupervised learning
dc.title.none.fl_str_mv Identifying Regional Trends in Avatar Customization
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Since virtual identities such as social media profiles and avatars have become a common venue for self-expression, it has become important to consider the ways in which existing systems embed the values of their designers. In order to design virtual identity systems that reflect the needs and preferences of diverse users, understanding how the virtual identity construction differs between groups is important. This paper presents a new methodology that leverages deep learning and differential clustering for comparative analysis of profile images, with a case study of almost 100 000 avatars from a large online community using a popular avatar creation platform. We use novelty discovery to segment the avatars, then cluster avatars by region to identify visual trends among low-and high-novelty avatars. We find that avatar customization correlates with increased social activity, and we are able to identify distinct visual trends among the U.S.-region and Japan-region profiles. Among these trends, realistic, idealistic, and creative self-representation can be distinguished. We observe that the realistic self-expression mirrors regional demographics, idealistic self-expression reflects shared mass-media tropes, and creative self-expression propagates within the communities.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Transactions on Games<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/tg.2018.2835776" target="_blank">https://dx.doi.org/10.1109/tg.2018.2835776</a></p>
eu_rights_str_mv openAccess
id Manara2_57e9d24ecd781e43fc813ff58d4e437b
identifier_str_mv 10.1109/tg.2018.2835776
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25886920
publishDate 2019
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Identifying Regional Trends in Avatar CustomizationPeter Mawhorter (18602944)Sercan Sengun (18602947)Haewoon Kwak (5747558)D. Fox Harrell (18602950)Information and computing sciencesHuman-centred computingAvatarsSocial network servicesGamesMachine learningTrainingMarket researchPrototypesArtificial neural networksclustering algorithmscultural differencesdata analysisdeep learningimage processingunsupervised learning<p dir="ltr">Since virtual identities such as social media profiles and avatars have become a common venue for self-expression, it has become important to consider the ways in which existing systems embed the values of their designers. In order to design virtual identity systems that reflect the needs and preferences of diverse users, understanding how the virtual identity construction differs between groups is important. This paper presents a new methodology that leverages deep learning and differential clustering for comparative analysis of profile images, with a case study of almost 100 000 avatars from a large online community using a popular avatar creation platform. We use novelty discovery to segment the avatars, then cluster avatars by region to identify visual trends among low-and high-novelty avatars. We find that avatar customization correlates with increased social activity, and we are able to identify distinct visual trends among the U.S.-region and Japan-region profiles. Among these trends, realistic, idealistic, and creative self-representation can be distinguished. We observe that the realistic self-expression mirrors regional demographics, idealistic self-expression reflects shared mass-media tropes, and creative self-expression propagates within the communities.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Transactions on Games<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/tg.2018.2835776" target="_blank">https://dx.doi.org/10.1109/tg.2018.2835776</a></p>2019-12-04T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/tg.2018.2835776https://figshare.com/articles/journal_contribution/Identifying_Regional_Trends_in_Avatar_Customization/25886920CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/258869202019-12-04T03:00:00Z
spellingShingle Identifying Regional Trends in Avatar Customization
Peter Mawhorter (18602944)
Information and computing sciences
Human-centred computing
Avatars
Social network services
Games
Machine learning
Training
Market research
Prototypes
Artificial neural networks
clustering algorithms
cultural differences
data analysis
deep learning
image processing
unsupervised learning
status_str publishedVersion
title Identifying Regional Trends in Avatar Customization
title_full Identifying Regional Trends in Avatar Customization
title_fullStr Identifying Regional Trends in Avatar Customization
title_full_unstemmed Identifying Regional Trends in Avatar Customization
title_short Identifying Regional Trends in Avatar Customization
title_sort Identifying Regional Trends in Avatar Customization
topic Information and computing sciences
Human-centred computing
Avatars
Social network services
Games
Machine learning
Training
Market research
Prototypes
Artificial neural networks
clustering algorithms
cultural differences
data analysis
deep learning
image processing
unsupervised learning