This thesis examines whether a data mining approach, such as natural language processing, can help the founders of crowdfunding campaigns be more successful.
In a data mining framework 493,324 campaigns of the two popular crowdfunding platforms Kickstarter and Indiegogo were analyzed by natural language processing using different artificial neural networks to obtain the information needed by the founders. For frequently occurring categories, a reliable classification of the category was possible. For rare ones it was less precise. It was also shown that the more a founder concentrates on a specific category when setting up a campaign, the more likely it was that a campaign would be successful. A prediction of campaign success was also possible but was influenced by the nature of the data set. It was demonstrated that this approach could generate important information that could lead to a competitive advantage of the founders for most of the campaigns in the dataset.
Crowdfunding is an emerging industry which has gained considerable attention in recent years. Competition among campaigns and founders will therefore become increasingly intense. This means, that founders must gain a competitive advantage over the competitors to be successful. Data mining approaches which also include natural language processing could be suitable to assist the founders with valuable information when setting up campaigns and thus enable them to gain a competitive advantage. Especially the right categorization on a crowdfunding platform and prediction of success are important information to support the founders.
Table of Contents
1. Introduction
2. Theoretical Foundation
2.1. Data Mining Process
2.2. Natural Language Processing
2.2.1. Definition and Distinction
2.2.2. Preprocessing and Feature Selection
2.2.3. Vectorization of Words
2.3. Architecture and Types of Artificial Neural Networks
2.3.1. Feed Forward Neural Networks
2.3.2. Convolutional Neural Networks
2.3.3. Graph Neural Networks
2.3.4. Recurrent Neural Networks
2.3.5. Methods for Performance Evaluation
2.4. Applied technologies
3. Methodology
3.1. Business Understanding
3.2. Data Understanding
3.3. Data Preparation
3.4. Modeling
3.4.1. Convolutional Neural Networks
3.4.2. Graph Neural Networks
3.4.3. Bidirectional LSTM
4. Evaluation of Results
4.1. Convolutional Neural Network Results
4.1.1. Category Prediction by Convolutional Neural Network
4.1.2. Success Prediction by Convolutional Neural Network
4.2. Graph Convolutional Neural Network Results
4.2.1. Category Prediction by Graph Convolutional Neural Network
4.2.2. Success Prediction by Convolutional Neural Network
4.3. Bidirectional LSTM Results
4.3.1. Category Prediction by Bidirectional LSTM
4.3.2. Success Prediction by Bidirectional LSTM
5. Discussion
6. Conclusion and Outlook
Objective & Topics
This thesis investigates whether natural language processing (NLP) techniques applied to user-generated campaign text can assist crowdfunding founders by predicting appropriate categories and overall campaign success. The study aims to provide a competitive advantage to founders by leveraging data mining frameworks to turn unstructured textual descriptions into actionable insights.
- Application of the CRISP-DM framework to crowdfunding data.
- Implementation and comparison of Convolutional Neural Networks (CNN), Graph Convolutional Neural Networks (GCN), and Bidirectional LSTM models.
- Analysis of dataset imbalances on predictive model performance.
- Evaluation of "typicality" and "ambiguity" metrics in relation to campaign success.
Excerpt from the Thesis
3.1. Business Understanding
The data analyzed in this thesis originates from the two crowdfunding platforms Indiegogo (IG) and Kickstarter (KS). Crowdfunding allows a crowd of internet users to finance initiatives. Fundings are often requested on platforms such as KS or IG. Artists, activists, organizers and entrepreneurs, to name only a few, can present their projects on these platforms through campaigns and specify a target sum of funds needed to be able to realize their project. If the target sum is reached within a set period, it can be said that the funding was successful. Both platforms differ in this respect. On Kickstarter, the funds are only released if the goal has been reached after the funding period has expired. On Indiegogo, the funds can be granted even if the goal has not been reached by the end of the funding period. In addition, each campaign is assigned to a primary category and a subcategory. This makes it possible to specifically search for specific campaigns on the platforms. More detailed characteristics can be described through media such as text, images and videos.
One hypothesis is that the text, which is created by the founder, contains information that makes it possible to categorize the campaigns in the appropriate category and draw conclusions about the success. These information in the text consist of e.g. risks, budget, schedule, history, motivation and team presentation. Figure 18 illustrates the hypothesis schematically.
If this hypothesis proves to be true, the founders can be helped to set up the campaigns correctly and also get an indication whether a campaign will be successful before the campaign starts. In addition, investors could also determine whether a campaign will be successful or not and hence whether an investment is worthwhile.
Summary of Chapters
1. Introduction: Outlines the growth of the crowdfunding market, the problem of selecting the right categories, and sets the research questions regarding NLP's ability to predict categorization and campaign success.
2. Theoretical Foundation: Provides the conceptual background on the CRISP-DM framework, natural language processing techniques, and the architectural details of various artificial neural networks.
3. Methodology: Details the practical implementation, including the business understanding, data sourcing from Kickstarter and Indiegogo, data cleaning processes, and the model architectures used.
4. Evaluation of Results: Presents the findings from the neural network experiments, comparing model performance across categories and success objectives using test accuracy and F1 scores.
5. Discussion: Interprets the results within the research context, addressing the impact of data imbalance and hyperparameter tuning on model reliability.
6. Conclusion and Outlook: Synthesizes the main findings, confirms the effectiveness of BI-LSTM models, and suggests future research directions, such as Hierarchical Neural Networks.
Keywords
Crowdfunding, Natural Language Processing, Artificial Neural Network, Kickstarter, Indiegogo, CRISP-DM, Data Mining, Convolutional Neural Networks, Graph Convolutional Networks, Bidirectional LSTM, Success Prediction, Text Classification, Hyperparameter Tuning, Deep Learning, Feature Selection
Frequently Asked Questions
What is the primary focus of this research?
The research explores the application of natural language processing on user-generated text from crowdfunding campaigns to identify patterns that predict campaign categorization and financial success.
Which crowdfunding platforms were analyzed for this study?
The study utilizes datasets from Kickstarter (KS) and Indiegogo (IG).
What is the core research question addressed by the thesis?
The thesis answers two main questions: Can NLP predict the category for a given campaign, and can it predict whether a campaign will reach its funding target?
Which machine learning architectures were employed?
The author implemented and evaluated three distinct architectures: Convolutional Neural Networks (CNN), Graph Convolutional Neural Networks (GCN), and Bidirectional Long Short-Term Memory networks (BI-LSTM).
How is the methodology structured?
The analysis follows the standardized Cross-Industry Standard Process for Data Mining (CRISP-DM), moving through phases of business understanding, data collection, preparation, and modeling.
Which performance metrics were used to determine model quality?
Model success was primarily evaluated using test accuracy and F1 scores, with secondary analysis of typicality and entropy metrics to assess prediction confidence.
Which model provided the best overall performance?
The BI-LSTM architecture consistently achieved the highest test accuracy and F1 scores across both objectives and datasets.
How does the author propose dealing with dataset imbalance?
The author acknowledges that dataset imbalance affects results, particularly for rare categories, and discusses weight balancing as a potential mitigation strategy to improve predictive accuracy for minority classes.
- Arbeit zitieren
- Benjamin Brummer (Autor:in), 2021, Crowdfunding Campaigns. Success Prediction Through Natural Language Processing, München, GRIN Verlag, https://www.grin.com/document/1382124
