Classifying Three Tiers of Success in Crowdfunding with Machine Learning and Natural Language Processing
| dc.contributor.advisor | Axtell, Robert L. | |
| dc.contributor.author | Wong, Sze Wing | |
| dc.creator | Wong, Sze Wing | |
| dc.date.accessioned | 2022-08-03T20:18:30Z | |
| dc.date.available | 2022-08-03T20:18:30Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | With the continued growing adoption of crowdfunding for raising capital, much research and numerous studies have been done using econometric analyses and traditional machine learning models to identify key indicators and to classify success in campaigns. These findings are informative and hold beneficial insights for both entrepreneurs and investors. However, in recent years, the increasing number of successful campaigns far exceeds the number of failed campaigns. Therefore, previous studies focusing on binary classification are no longer sufficient to capture different levels of emergent success in crowdfunding. This dissertation examines three tiers of success in reward-based campaigns of the 2019 Kickstarter data to gain insights into the evolved crowdfunding phenomenon. How I demonstrate new key indicators are identified by exploiting campaign information relates to “people” versus “products” with hierarchical multiple and ordinal logistic regressions. In conjunction, I adopt Binary Particle Swarm Optimization (BPSO) for feature selection to classify campaign success. The BPSO improved Extreme Gradient Boosting (XGBoost) classifier shows favorable model performance in multiclass classification. Most importantly, the interest in this research extends beyond using categorical and numeric features but also fuses multiple textual information with natural language processing (NLP) and deep neural networks (DNNs) for multiclass classification. The proposed multimodal Long Short Term Memory (LSTM) concatenates BPSO selected metadata with the project’s pitch and the creator’s biography text yields the best performing multiclass classification accuracy of 71.04% after tuning. However, the BPSO improved Extreme Gradient Boosting (XGBoost) classifier achieves the highest accuracy of 74.61% overall. These impactful findings allow entrepreneurs and researchers to gain further insights and to optimize the cyber marketing space effectively. | |
| dc.format.extent | 187 pages | |
| dc.identifier.uri | https://hdl.handle.net/1920/12934 | |
| dc.language.iso | en | |
| dc.rights | Copyright 2021 Sze Wing Wong | |
| dc.subject | Computer science | |
| dc.subject | Economics | |
| dc.subject | Binary Particle Swarm Optimization | |
| dc.subject | Crowdfunding | |
| dc.subject | Deep Learning | |
| dc.subject | Machine learning | |
| dc.subject | Multimodal | |
| dc.subject | Natural Language Processing | |
| dc.title | Classifying Three Tiers of Success in Crowdfunding with Machine Learning and Natural Language Processing | |
| dc.type | Dissertation | |
| thesis.degree.discipline | Computational Sciences and Informatics | |
| thesis.degree.grantor | George Mason University | |
| thesis.degree.level | Ph.D. | |
| thesis.degree.name | Ph.D. in Computational Sciences and Informatics |
Files
Original bundle
1 - 1 of 1