Can Title Images Predict the Emotions and the Performance of Crowdfunding Projects?

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.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 10 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.