A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects
Identifying fraudulent campaigns or messages remains a difficult task in the field of natural language processing. We proposed a hypothesis that if the well-known brands in the same category as the crowdfunding project can implement similar technology as crowdfunding projects, the project is consi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Prince of Songkla University
2022-10-01
|
| Series: | Songklanakarin Journal of Science and Technology (SJST) |
| Subjects: | |
| Online Access: | https://sjst.psu.ac.th/journal/44-5/7.pdf |
| _version_ | 1797840047323480064 |
|---|---|
| author | Qi Li Jian Qu |
| author_facet | Qi Li Jian Qu |
| author_sort | Qi Li |
| collection | DOAJ |
| description | Identifying fraudulent campaigns or messages remains a difficult task in the field of natural language processing. We
proposed a hypothesis that if the well-known brands in the same category as the crowdfunding project can implement similar
technology as crowdfunding projects, the project is considered to be more feasible. The opposite is considered more likely to be
fraudulent. This research proposed a novel BNB-NO-BK method to detect fraudulent crowdfunding projects. A novel method
called BNB, which was constructed by key-BERT, NLTK, and fine-tuned QA model for BERT, was proposed to extract the
characteristics of crowdfunding projects. We proposed a novel NO (Nice Classification & Ontology) method for classifying the
categories of projects, which constructed ontology trees based on the characteristics of the crowdfunding projects and our
modified Nice Classification. Furthermore, we proposed a novel BK (Brand Knowledge) cross-checking method to extract the
features of crowdfunding projects. Finally, we compared the performances of different machine learning methods for identifying
fraudulent crowdfunding projects. Furthermore, to address the problem of possible bias caused by unbalanced data, we used data
augmentation to process the dataset. Our proposed method achieved an accuracy of 95.71% in detecting fraudulent crowdfunding
projects, which was superior to existing methods. |
| first_indexed | 2024-04-09T16:08:08Z |
| format | Article |
| id | doaj.art-f5f6b2ffae684e72af71f03217c5c79b |
| institution | Directory Open Access Journal |
| issn | 0125-3395 |
| language | English |
| last_indexed | 2024-04-09T16:08:08Z |
| publishDate | 2022-10-01 |
| publisher | Prince of Songkla University |
| record_format | Article |
| series | Songklanakarin Journal of Science and Technology (SJST) |
| spelling | doaj.art-f5f6b2ffae684e72af71f03217c5c79b2023-04-25T03:47:25ZengPrince of Songkla UniversitySongklanakarin Journal of Science and Technology (SJST)0125-33952022-10-014451209121910.14456/sjst-psu.2022.157A novel BNB-NO-BK method for detecting fraudulent crowdfunding projectsQi Li0Jian Qu1School of Engineering and Technology, Panyapiwat Institute of Management, Pak Kret, Nonthaburi, 11120 ThailandSchool of Engineering and Technology, Panyapiwat Institute of Management, Pak Kret, Nonthaburi, 11120 ThailandIdentifying fraudulent campaigns or messages remains a difficult task in the field of natural language processing. We proposed a hypothesis that if the well-known brands in the same category as the crowdfunding project can implement similar technology as crowdfunding projects, the project is considered to be more feasible. The opposite is considered more likely to be fraudulent. This research proposed a novel BNB-NO-BK method to detect fraudulent crowdfunding projects. A novel method called BNB, which was constructed by key-BERT, NLTK, and fine-tuned QA model for BERT, was proposed to extract the characteristics of crowdfunding projects. We proposed a novel NO (Nice Classification & Ontology) method for classifying the categories of projects, which constructed ontology trees based on the characteristics of the crowdfunding projects and our modified Nice Classification. Furthermore, we proposed a novel BK (Brand Knowledge) cross-checking method to extract the features of crowdfunding projects. Finally, we compared the performances of different machine learning methods for identifying fraudulent crowdfunding projects. Furthermore, to address the problem of possible bias caused by unbalanced data, we used data augmentation to process the dataset. Our proposed method achieved an accuracy of 95.71% in detecting fraudulent crowdfunding projects, which was superior to existing methods.https://sjst.psu.ac.th/journal/44-5/7.pdfcrowdfunding projectsfine-tunebert qa modelontologybrand information retrievalmachine learning classifier |
| spellingShingle | Qi Li Jian Qu A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects Songklanakarin Journal of Science and Technology (SJST) crowdfunding projects fine-tunebert qa model ontology brand information retrieval machine learning classifier |
| title | A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
| title_full | A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
| title_fullStr | A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
| title_full_unstemmed | A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
| title_short | A novel BNB-NO-BK method for detecting fraudulent crowdfunding projects |
| title_sort | novel bnb no bk method for detecting fraudulent crowdfunding projects |
| topic | crowdfunding projects fine-tunebert qa model ontology brand information retrieval machine learning classifier |
| url | https://sjst.psu.ac.th/journal/44-5/7.pdf |
| work_keys_str_mv | AT qili anovelbnbnobkmethodfordetectingfraudulentcrowdfundingprojects AT jianqu anovelbnbnobkmethodfordetectingfraudulentcrowdfundingprojects AT qili novelbnbnobkmethodfordetectingfraudulentcrowdfundingprojects AT jianqu novelbnbnobkmethodfordetectingfraudulentcrowdfundingprojects |