A computational visual analysis of image design in social media car model communities

Jochen Wulf; Tobias Mettler; Stephan Ludwig; Dennis Herhausen

A computational visual analysis of image design in social media car model communities

Jochen Wulf, Tobias Mettler, Stephan Ludwig, Dennis Herhausen

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

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 image popularity. 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 popularity that relate to the levels of utility reference, 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 content popularity in social media. The proposed computational visual analysis methodology may inform the study of other image-based IS.

Original language	English
Title of host publication	Proceedings of the 27th European Conference on Information Systems
Subtitle of host publication	Information Systems for a Sharing Society, ECIS 2019
Editors	Jan vom Brocke, Shirley Gregor, Oliver Muller
Place of Publication	Sweden
Publisher	Association for Information Systems
ISBN (Electronic)	9781733632508
Publication status	Published - 2019
Externally published	Yes
Event	European Conference on Information Systems 2019: Information Systems for a Sharing Society - Stockholm and Uppsala, Sweden Duration: 8 Jun 2019 → 14 Jun 2019 Conference number: 27th http://ecis2019.eu/

Conference

Conference	European Conference on Information Systems 2019
Abbreviated title	ECIS 2019
Country/Territory	Sweden
City	Stockholm and Uppsala
Period	8/06/19 → 14/06/19
Internet address	http://ecis2019.eu/

Keywords

Computational visual analysis
Convolutional neural networks
Image analysis
Product communities
Social media

Access to Document

https://aisel.aisnet.org/ecis2019_rp/168/

Cite this

Wulf, J., Mettler, T., Ludwig, S., & Herhausen, D. (2019). A computational visual analysis of image design in social media car model communities. In J. vom Brocke, S. Gregor, & O. Muller (Eds.), Proceedings of the 27th European Conference on Information Systems: Information Systems for a Sharing Society, ECIS 2019 Association for Information Systems. https://aisel.aisnet.org/ecis2019_rp/168/

Wulf, Jochen ; Mettler, Tobias ; Ludwig, Stephan et al. / A computational visual analysis of image design in social media car model communities. Proceedings of the 27th European Conference on Information Systems: Information Systems for a Sharing Society, ECIS 2019. editor / Jan vom Brocke ; Shirley Gregor ; Oliver Muller. Sweden : Association for Information Systems, 2019.

@inproceedings{b1e563c46a4843aba18b25124a8e051b,

title = "A computational visual analysis of image design in social media car model communities",

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 image popularity. 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 popularity that relate to the levels of utility reference, 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 content popularity in social media. The proposed computational visual analysis methodology may inform the study of other image-based IS.",

keywords = "Computational visual analysis, Convolutional neural networks, Image analysis, Product communities, Social media",

author = "Jochen Wulf and Tobias Mettler and Stephan Ludwig and Dennis Herhausen",

note = "Publisher Copyright: {\textcopyright} 27th European Conference on Information Systems - Information Systems for a Sharing Society, ECIS 2019. All rights reserved.; European Conference on Information Systems 2019 : Information Systems for a Sharing Society, ECIS 2019 ; Conference date: 08-06-2019 Through 14-06-2019",

year = "2019",

language = "English",

editor = "{vom Brocke}, Jan and Shirley Gregor and Oliver Muller",

booktitle = "Proceedings of the 27th European Conference on Information Systems",

publisher = "Association for Information Systems",

address = "United States of America",

url = "http://ecis2019.eu/",

}

Wulf, J, Mettler, T, Ludwig, S & Herhausen, D 2019, A computational visual analysis of image design in social media car model communities. in J vom Brocke, S Gregor & O Muller (eds), Proceedings of the 27th European Conference on Information Systems: Information Systems for a Sharing Society, ECIS 2019. Association for Information Systems, Sweden, European Conference on Information Systems 2019, Stockholm and Uppsala, Sweden, 8/06/19. <https://aisel.aisnet.org/ecis2019_rp/168/>

A computational visual analysis of image design in social media car model communities. / Wulf, Jochen; Mettler, Tobias; Ludwig, Stephan et al.
Proceedings of the 27th European Conference on Information Systems: Information Systems for a Sharing Society, ECIS 2019. ed. / Jan vom Brocke; Shirley Gregor; Oliver Muller. Sweden: Association for Information Systems, 2019.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

TY - GEN

T1 - A computational visual analysis of image design in social media car model communities

AU - Wulf, Jochen

AU - Mettler, Tobias

AU - Ludwig, Stephan

AU - Herhausen, Dennis

N1 - Conference code: 27th

PY - 2019

Y1 - 2019

N2 - 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 image popularity. 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 popularity that relate to the levels of utility reference, 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 content popularity in social media. The proposed computational visual analysis methodology may inform the study of other image-based IS.

AB - 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 image popularity. 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 popularity that relate to the levels of utility reference, 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 content popularity in social media. The proposed computational visual analysis methodology may inform the study of other image-based IS.

KW - Computational visual analysis

KW - Convolutional neural networks

KW - Image analysis

KW - Product communities

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85087104472&partnerID=8YFLogxK

M3 - Conference Paper

AN - SCOPUS:85087104472

BT - Proceedings of the 27th European Conference on Information Systems

A2 - vom Brocke, Jan

A2 - Gregor, Shirley

A2 - Muller, Oliver

PB - Association for Information Systems

CY - Sweden

T2 - European Conference on Information Systems 2019

Y2 - 8 June 2019 through 14 June 2019

ER -

A computational visual analysis of image design in social media car model communities

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this