Can title images predict the emotions and the performance of crowdfunding projects?

Jian Ren Hou, Jie Jennifer Zhang, Kunpeng Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Crowdfunding is a novel way to raise funds from individuals. However, taking Kickstarter for example, more than 60% of projects failed to reach the funding targets. Hence it is imperative to study how to improve the successfulness of the projects. From a design perspective, we intend to investigate that can the characteristics of title images of the projects on the search page of the crowdfunding website predict the performance of crowdfunding projects. We use objective standards to measure the aesthetic features of the title images. And we introduce emotions as important antecedents for the performance of a project. We used deep learning to extract the emotion metrics from the title images. Analysis results provide significant evidence that aesthetic attributes of images can predict emotion in images, and emotions, such as sadness and contentment, can predict the performance of crowdfunding projects. Our results provide both theoretical and practical values.

Original languageEnglish
Title of host publicationProceedings of the 52nd Annual Hawaii International Conference on System Sciences, HICSS 2019
EditorsTung X. Bui
PublisherIEEE Computer Society
Pages4439-4448
Number of pages10
ISBN (Electronic)9780998133126
Publication statusPublished - 2019
Event52nd Annual Hawaii International Conference on System Sciences, HICSS 2019 - Maui, United States
Duration: 2019 Jan 82019 Jan 11

Publication series

NameProceedings of the Annual Hawaii International Conference on System Sciences
Volume2019-January
ISSN (Print)1530-1605

Conference

Conference52nd Annual Hawaii International Conference on System Sciences, HICSS 2019
Country/TerritoryUnited States
CityMaui
Period19-01-0819-01-11

All Science Journal Classification (ASJC) codes

  • General Engineering

Fingerprint

Dive into the research topics of 'Can title images predict the emotions and the performance of crowdfunding projects?'. Together they form a unique fingerprint.

Cite this