Extreme rainfall events are significant manifestations of climate change, causing substantial impacts on urban infrastructure and public life. This study takes the extreme rainfall event in Beijing in 2023 as the background and utilizes data from Sina Weibo. Based on large language models and prompt engineering, disaster information is extracted, and a multi-factor coupled disaster multi-sentiment classification model, Bert-BiLSTM, is designed. A disaster analysis framework focusing on three dimensions of theme, location and sentiment is constructed. The results indicate that during the pre-disaster stage, themes are concentrated on warnings and prevention, shifting to specific events and rescue actions during the disaster, and post-disaster, they express gratitude to rescue personnel and highlight social cohesion. In terms of spatial location, the disaster shows significant clustering, predominantly occurring in Mentougou and Fangshan. There is a clear difference in emotional expression between official media and the public; official media primarily focuses on neutral reporting and fact dissemination, while public sentiment is even richer. At the same time, there are also variations in sentiment expressions across different affected regions. This study provides new perspectives and methods for analyzing extreme rainfall events on social media by revealing the evolution of disaster themes, the spatial distribution of disasters, and the temporal and spatial changes in sentiment. These insights can support risk assessment, resource allocation, and public opinion guidance in disaster emergency management, thereby enhancing the precision and effectiveness of disaster response strategies.

Based on Weibo big data, BERTopic, and dual-channel sentiment analysis model, a dynamic analysis framework of public perception and emotion evolution is constructed from the perspective of disaster chain and public response. The results show that (1) Due to the trust of information sources by the public, the efficiency of early warning information reaching the public and attracting attention is relatively high. Social media activity on related topics peaked several times in response to reports of major hazards, such as railway suspensions, passengers trapped in trains, and severe flooding in Miyun District, Beijing. (2) The evolution of topics of public attention strongly corresponds to the disaster process: From early warning and emergency risk avoidance, gradually move to disaster report and rescue coordination, and finally focus on the criticism of infrastructure vulnerability. (3) The emotional response presents phased characteristics. At the initial stage of the rainstorm red warning issued by the meteorological department, anxiety is dominant; after the release of rescue information, emotion rises briefly, and reflection and attribution tendencies generally appear after the disaster. (4) Elderly populations and those in remote areas exhibit characteristics of vulnerability, information isolation, and high dependency in response to disasters.