|
A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Qi Li 2. Jian Qu |
| Title | A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2565 |
| Journal Title | Songklanakarin Journal of Science an Technology (SJST) |
| Journal Vol. | 44 |
| Journal No. | 5 |
| Page no. | 1209-1219 |
| Keyword | crowdfunding projects, fine-tuneBert QA model, ontology, brand information retrieval, machine learning classifier |
| URL Website | https://sjst.psu.ac.th/ |
| ISSN | 0125-3395 |
| Abstract | Identifying fraudulent campaigns or messages remains a difficult task in the field of natural language processing. Weproposed a hypothesis that if the well-known brands in the same category as the crowdfunding project can implement similartechnology as crowdfunding projects, the project is considered to be more feasible. The opposite is considered more likely to befraudulent. This research proposed a novel BNB-NO-BK method to detect fraudulent crowdfunding projects. A novel methodcalled BNB, which was constructed by key-BERT, NLTK, and fine-tuned QA model for BERT, was proposed to extract thecharacteristics of crowdfunding projects. We proposed a novel NO (Nice Classification & Ontology) method for classifying thecategories of projects, which constructed ontology trees based on the characteristics of the crowdfunding projects and ourmodified Nice Classification. Furthermore, we proposed a novel BK (Brand Knowledge) cross-checking method to extract thefeatures of crowdfunding projects. Finally, we compared the performances of different machine learning methods for identifyingfraudulent crowdfunding projects. Furthermore, to address the problem of possible bias caused by unbalanced data, we used dataaugmentation to process the dataset. Our proposed method achieved an accuracy of 95.71% in detecting fraudulent crowdfundingprojects, which was superior to existing methods. |
