學術產出-會議論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Can Generative AI Eliminate Speech Harms? A Study on Detection of Abusive and Hate Speech during the COVID-19 Pandemic
作者 楊亨利;李博逸
Yang, Heng-Li;Li, Bo-Yi;Wang, Chen-Shu;Chen, Hong-Yan
貢獻者 資管博六
關鍵詞 Abusive and hate speech; Machine learning; Language model
日期 2023-10
上傳時間 2024-07-17
摘要 This study investigates the issue of abusive and hateful language arising from the COVID-19 pandemic, this research employs machine learning techniques to establish a system capable of detecting and rephrasing abusive and hateful language. To begin, a dataset and dictionary specific to abusive and hateful language in Chinese. Subsequently, a two-stage detection model is proposed, with the BERT model yielding the most optimal outcomes. The first stage attains an accuracy of 94.42%, while the second stage achieves an accuracy of 81.48%.
關聯 2023 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), IEEE
資料類型 conference
DOI https://doi.org/10.1109/ICCE-Asia59966.2023.10326404
dc.contributor 資管博六
dc.creator (作者) 楊亨利;李博逸
dc.creator (作者) Yang, Heng-Li;Li, Bo-Yi;Wang, Chen-Shu;Chen, Hong-Yan
dc.date (日期) 2023-10
dc.date.accessioned 2024-07-17-
dc.date.available 2024-07-17-
dc.date.issued (上傳時間) 2024-07-17-
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/152360-
dc.description.abstract (摘要) This study investigates the issue of abusive and hateful language arising from the COVID-19 pandemic, this research employs machine learning techniques to establish a system capable of detecting and rephrasing abusive and hateful language. To begin, a dataset and dictionary specific to abusive and hateful language in Chinese. Subsequently, a two-stage detection model is proposed, with the BERT model yielding the most optimal outcomes. The first stage attains an accuracy of 94.42%, while the second stage achieves an accuracy of 81.48%.
dc.format.extent 116 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) 2023 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), IEEE
dc.subject (關鍵詞) Abusive and hate speech; Machine learning; Language model
dc.title (題名) Can Generative AI Eliminate Speech Harms? A Study on Detection of Abusive and Hate Speech during the COVID-19 Pandemic
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/ICCE-Asia59966.2023.10326404
dc.doi.uri (DOI) https://doi.org/10.1109/ICCE-Asia59966.2023.10326404