A PERSUASION-BASED FRAMEWORK FOR PREDICTING CROWDFUNDING SUCCESS

52 Pages Posted: 20 Dec 2023

See all articles by HAOYU YUAN

HAOYU YUAN

Tsinghua University - Department of Management Science and Engineering

Dandan Qiao

National University of Singapore (NUS)

Qiang Wei

Tsinghua University - School of Economics & Management

Date Written: December 8, 2023

Abstract

While previous literature has explored different factors that influence crowdfunding, project initiators often find it challenging to manipulate these factors in their project designs to enhance funding support due to various reasons. Considering the vital role project descriptions play as a channel for backers to acquire relevant information and make funding decisions, our study seeks to fill this gap by investigating the impact of project descriptions through the lens of persuasion theory. To accomplish this goal, we propose a prediction approach that aligns with Aristotle’s persuasion trinity. By introducing designs such as label-based attention mechanism, mix-up training strategy and progressive learning strategy, our approach can well address the diversity and hybridity issues in persuasion identification. It enables us to discern how different persuasion tactics are expressed in project descriptions and further predict crowdfunding outcomes. Through a series of experiments, we have demonstrated the superior performance of our approach in both tasks: namely crowdfunding prediction and persuasive elements identification. Furthermore, our approach offers project initiators an automatic tool to obtain concrete guidelines for updating their project descriptions and enhancing persuasiveness to attract funding support. As a result, this study contributes both academically and practically by providing valuable insights to crowdfunding platforms.

Keywords: crowdfunding, persuasion, attention mechanism, mix-up, deep learning

JEL Classification: M15

Suggested Citation

YUAN, HAOYU and Qiao, Dandan and Wei, Qiang, A PERSUASION-BASED FRAMEWORK FOR PREDICTING CROWDFUNDING SUCCESS (December 8, 2023). Available at SSRN: https://ssrn.com/abstract=4658668 or http://dx.doi.org/10.2139/ssrn.4658668

HAOYU YUAN (Contact Author)

Tsinghua University - Department of Management Science and Engineering ( email )

United States

Dandan Qiao

National University of Singapore (NUS) ( email )

13 computing drive
Singapore, 117591
Singapore

Qiang Wei

Tsinghua University - School of Economics & Management ( email )

Beijing, 100084
China
+86-10-62789824 (Phone)
+86-10-62771647 (Fax)

HOME PAGE: http://www.sem.tsinghua.edu.cn/en/weiq

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
50
Abstract Views
172
PlumX Metrics