To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Federated Learning and LLM-based Social Media Comment Classification System Using Crowdsourcing Techniques |
|
Author |
Jungho Kang |
| Citation |
Vol. 24 No. 10 pp. 25-31 |
|
Abstract |
Currently, on social media, malicious comments have emerged as a serious issue. Existing artificial intelligence-based comment classification systems have limitations due to data bias and overfitting. To address this, this study proposed a novel comment classification system that combines crowdsourcing and federated learning. This system collects data from various users and utilizes a large language model like KoBERT through federated learning to classify comments accurately while protecting user privacy. It is expected to provide higher accuracy than existing methods and improve significantly the efficiency of detecting malicious comments. The proposed system can be applied to social media platforms and online communities. |
|
Keywords |
SNS, Comment Classification, Crowdsourcing, LLM-based KoBERT, Federated Learning |
|
URL |
