Browse by author
Lookup NU author(s): Professor Stuart Barnes
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
© 2024, Emerald Publishing Limited.Purpose: Color psychology theory reveals that complex images with very varied palettes and many different colors are likely to be considered unattractive by individuals. Notwithstanding, web content containing social signals may be more attractive via the initiation of a social connection. This research investigates a predictive model blending variables from these theoretical perspectives to determine crowdfunding success. Design/methodology/approach: The research is based on data from 176,614 Kickstarter projects. A number of machine learning and artificial intelligence techniques were employed to analyze the listing images for color complexity and the presence of people, while specific language features, including socialness, were measured in the listing text. Logistic regression was applied, controlling for several additional variables and predictive model was developed. Findings: The findings supported the color complexity and socialness effects on crowdfunding success. The model achieves notable predictive value explaining 56.4% of variance. Listing images containing fewer colors and that have more similar colors are more likely to be crowdfunded successfully. Listings that convey greater socialness have a greater likelihood of being funded. Originality/value: This investigation contributes a unique understanding of the effect of features of both socialness and color complexity on the success of crowdfunding ventures. A second contribution comes from the process and methods employed in the study, which provides a clear blueprint for the processing of large-scale analysis of soft information (images and text) in order to use them as variables in the scientific testing of theory.
Author(s): Barnes SJ
Publication type: Article
Publication status: Published
Journal: Industrial Management and Data Systems
Year: 2024
Volume: 124
Issue: 3
Pages: 1179-1202
Online publication date: 24/01/2024
Acceptance date: 02/04/2018
Date deposited: 12/02/2024
ISSN (print): 0263-5577
Publisher: Emerald Publishing
URL: https://doi.org/10.1108/IMDS-07-2023-0517
DOI: 10.1108/IMDS-07-2023-0517
Altmetrics provided by Altmetric
