A computational visual analysis of image design in social media

Details

Ressource 1Download: A COMPUTATIONAL VISUAL ANALYSIS OF IMAGE DESIGN IN SOCIAL MEDIA C.pdf (419.81 [Ko])
State: Public
Version: Final published version
License: Not specified
Serval ID
serval:BIB_D32D3DAB8CE7
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
A computational visual analysis of image design in social media
Title of the conference
Proceedings of the 27th European Conference on Information Systems
Author(s)
Wulf Jochen, Mettler Tobias, Ludwig Stephan, Herhausen Dennis
Publisher
Association for Information Systems
Organization
27th European Conference on Information Systems
Address
Stockholm University
ISBN
978-1-7336325-0-8
Publication state
Published
Issued date
15/05/2019
Peer-reviewed
Oui
Series
ECIS 2019 Proceedings
Pages
1-16
Language
english
Abstract
While user-generated images represent important information sources in IS in general and in social media in particular, there is little research that analyzes image design and its effects on virality. We introduce an innovative computational approach to extract image design characteristics that includes convolutional neural network-based image classification, a dimensionality reduction via principal component analysis, manual measurement validation, and a regression analysis. An analysis of 790,775 car images from 17 brands posted in 68 car model communities on a social media platform reveals several effects of product presentation on image virality that relate to the levels of utility refer- ence, experience reference, and visual detail. A comparison of economy cars and premium cars shows that car class moderates these image design effects. Our results contribute to the extant literature on brand communities and virality in social media. The proposed computational visual analysis method- ology may inform the study of other image-based IS.
Keywords
computational visual analysis, product communities, image analysis, social media, convolutional neural networks
Create date
05/03/2019 8:56
Last modification date
20/08/2019 15:53
Usage data