Social media is increasingly being used to obtain timely flood information to assist flood disaster management and situational awareness. However, since data in social media are massive, redundant, and unstructured, it is tricky to intuitively and clearly obtain effective information. To automatically obtain clear flood information and deduce flood development processes from social media, the authors of this paper propose an event-based and multi-level modeling approach including a data model and two methods. Through the hierarchical division of events (division into spatial object, phase, and attribute status), the flood information structure (including time, space, topic, emotion, and disaster condition) is defined. We built an entity construction method and a development process deduction method to achieve the automatic transition from cluttered data to orderly flood development processes. Taking the flooding event of the Yangtze and Huai Rivers in 2020 as an example, we successfully obtained true flood information and development process from social media data, which verified the effectiveness of the model and methods. Meanwhile, spatiotemporal pattern mining was carried out by using entities from different levels. The results showed that the flood was from west to east and the damage level was positively correlated with the number of flood-related social media texts, especially emotional texts. In summary, through the model and methods in this paper, clear flood information and dynamic development processes can be quickly and automatically obtained, and the spatiotemporal patterns of flood entities can be examined. It is beneficial to extract timely flood information and public sentiments towards flood events in order to perform better disaster relief and post-disaster management.

The rapid development of information technology has made the amount of information in massive texts far exceed human intuitive cognition, and dependency parsing can effectively deal with information overload. In the background of domain specialization, the migration and application of syntactic treebanks and the speed improvement in syntactic analysis models become the key to the efficiency of syntactic analysis. To realize domain migration of syntactic tree library and improve the speed of text parsing, this paper proposes a novel approach—the Double-Array Trie and Multi-threading (DAT-MT) accelerated graph fusion dependency parsing model. It effectively combines the specialized syntactic features from small-scale professional field corpus with the generalized syntactic features from large-scale news corpus, which improves the accuracy of syntactic relation recognition. Aiming at the problem of high space and time complexity brought by the graph fusion model, the DAT-MT method is proposed. It realizes the rapid mapping of massive Chinese character features to the model’s prior parameters and the parallel processing of calculation, thereby improving the parsing speed. The experimental results show that the unlabeled attachment score (UAS) and the labeled attachment score (LAS) of the model are improved by 13.34% and 14.82% compared with the model with only the professional field corpus and improved by 3.14% and 3.40% compared with the model only with news corpus; both indicators are better than DDParser and LTP 4 methods based on deep learning. Additionally, the method in this paper achieves a speedup of about 3.7 times compared to the method with a red-black tree index and a single thread. Efficient and accurate syntactic analysis methods will benefit the real-time processing of massive texts in professional fields, such as multi-dimensional semantic correlation, professional feature extraction, and domain knowledge graph construction.

1. As a fundamental method in spatial data mining, spatial clustering supports extensive applications across various fields, such as geoscience (Zhao et al. 2025), economics (Zhou, Yang, and Chang ...