Dissertation/ Thesis

MoneyMouth: A Machine Learning Analysis of Altruistic Crowdfunding Success on GlobalGiving.org

Bibliographic Details
Title: MoneyMouth: A Machine Learning Analysis of Altruistic Crowdfunding Success on GlobalGiving.org
Authors: Adib-Azpeitia, Danya, Hancock, Jeffrey, Wu, Jiajun
Publisher Information: Stanford Digital Repository, 2025.
Publication Year: 2025
Subject Terms: Crowd funding, Deep learning (Machine learning), Communication, Machine learning, Statistics, FOS: Mathematics, Altruism, Social service, Social sciences--Statistical methods--Computer programs
Description: NGOs often face knowledge barriers regarding how to write effective fundraising requests on crowdfunding platforms. This issue motivates the use of mixed computational methods to identify the linguistic features associated with successful campaigns and predict whether a campaign will succeed. The research incorporates Linguistic Inquiry and Word Count (LIWC), Pearson correlation coefficients (PCC), logistic regression (LR), Bidirectional Encoder Representations from Transformers (BERT), and Local Interpretable Model-Agnostic Explanations (LIME) with the goal of unifying computer and social science. The PCCs calculated on GlobalGiving.org projects suggest that community-based thinking, storytelling, and readability are characteristics of campaigns that reach their target fundraising amount. The LR model’s most heavily-weighted linguistic features corroborate those results. The fine-tuned BERT model performed slightly better than the logistic regression at predicting a crowdfunding campaign’s success.
Document Type: Thesis
DOI: 10.25740/pm973nb1133
Rights: CC 0
Accession Number: edsair.doi...........8f2c229cf63629c189bcce5b386422e2
Database: OpenAIRE
Description
DOI:10.25740/pm973nb1133