Impact of difficult negatives on Twitter crisis detection

• Main Authors: ZHANG, Yuhao, LO, Siaw Ling, WIN MYINT, Phyo Yi
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2023
• 主題: Twitter; Crisis Detection; Difficult Negative Data; Negative Mining; Databases and Information Systems; Social Media
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8007; https://ink.library.smu.edu.sg/context/sis_research/article/9010/viewcontent/LoSiawLing_2023_Impact_of_Difficult_Negatives_on_Twitter_Crisis_Detection.pdf

Twitter has become an alternative information source during a crisis. However, the short, noisy nature of tweets hinders information extraction. While models trained with standard Twitter crisis datasets accomplished decent performance, it remained a challenge to generalize to unseen crisis events....