作者: Yu Zhang , Wenzhou Wu , Qi Wang , Fenzhen Su
DOI: 10.3390/SU9040534
关键词: Ontology 、 Semantic similarity 、 Event based 、 Data science 、 Computer science 、 Typhoon 、 Geospatial analysis 、 Social media 、 Leverage (statistics)
摘要: Social media is valuable in propagating information during disasters for its timely and available characteristics nowadays, assists making decisions when tagged with locations. Considering the ambiguity inaccuracy some social data, additional authoritative data are needed important verification. However, current works often fail to leverage both and, on most occasions, used disaster analysis after fact. Moreover, organize from perspective of spatial location, but not disaster, it difficult dynamically analyze disaster. All disaster-related around affected locations need be retrieved. To solve these limitations, this study develops a geo-event-based geospatial service (GEGIS) framework proceeded as follows: (1) geo-event-related ontology was constructed provide uniform semantic basis system; (2) geo-events attributes were extracted web using natural language process (NLP) similarity match resources; (3) prototype system designed implemented automatically retrieving organizing resources. A case typhoon hazard analyzed here within GEGIS shows that would effective typhoons occur.