The exploding popularity of social networks, provides a new opportunity to study disasters and public emotion. Among the social networks, Weibo is one of the largest microblogging services in China. Taking Guangdong and Guangxi in the south of China as a case, Web Scraper was used to obtain Weibo texts related to oods in 2020. The spatial distribution of oods was analyzed using Kernel Density Estimation.Public emotion was analyzed using Natural Language Processing (NLP) tools. The association between oods and public emotion was explored through correlation analysis methods. The results indicated that:(1) Weibo texts could be utilized as an effective data to identify urban waterlogging risk in Guangdong and Guangxi.(2) More oods occurred in the southeast than in the central and northwest, and more in the south than in the north in Guangdong and Guangxi. The coastal cities and provincial capitals were severely affected.(3) The public emotion was mainly negative and varied signi cantly over time, generally showing stronger negative emotion during periods of heavy precipitation. ( 4) There was a strong correlation between public emotion and oods in spatial-temporal variation. The degree of negative public emotion was signi cantly in uenced by the number of waterlogging points. The presented results serve as the pre-liminary data for future planning and designing of emergency management. HighlightsWeibo texts can be used to study the ooding situation and public emotion.The distribution of waterlogging points was spatially heterogeneous.The type of public response was dominated by the description of the ood.The overall public emotion during the ood was negative.There was a strong correlation between public emotion and ooding.

The exploding popularity of social networks, provides a new opportunity to study disasters and public emotion. Among the social networks, Weibo is one of the largest microblogging services in China. Taking Guangdong and Guangxi in the south of China as a case, Web Scraper was used to obtain Weibo texts related to floods in 2020. The spatial distribution of floods was analyzed using Kernel Density Estimation. Public emotion was analyzed using Natural Language Processing (NLP) tools. The association between floods and public emotion was explored through correlation analysis methods. The results indicated that: (1) Weibo texts could be utilized as an effective data to identify urban waterlogging risk in Guangdong and Guangxi. (2) More floods occurred in the southeast than in the central and northwest, and more in the south than in the north in Guangdong and Guangxi. The coastal cities and provincial capitals were severely affected. (3) The public emotion was mainly negative and varied significantly over time, generally showing stronger negative emotion during periods of heavy precipitation. (4) There was a strong correlation between public emotion and floods in spatial-temporal variation. The degree of negative public emotion was significantly influenced by the number of waterlogging points. The presented results serve as the pre-liminary data for future planning and designing of emergency management.