公众议题知识库的多层本体设计

Design of a Multi -layered Ontology for Public Issue Knowledge Base

公众议题知识库用于描述社会化媒体中讨论的公众事件、话题、参与议题的关键人员和机构,与之相关的时间、地点以及它们之间动态的关联。知识库的本体设计采用多层结构:核心层包含公众议题,即公众参与讨论的事件和话题,扩展层包含参与议题发展过程的关键人员、机构及地理位置,支撑层包含有关的微博文档。同时本体还描述时间维度,以支持对事件发展过程的表示和分析。知识库可以支持议题概貌、发展趋势、相关议题的查询与分析。

In order to capture the evolving public issues discussed in social media （including public events and topics）, we designed a knowledge-base, i. e., ontology, to capture public events and topics, individuals and organizations that play key roles in the development and evolvement of such events, and the dynamic interactions among them. Our design structures the ontology into multiple layers： the basic layer includes public issues; the extended layer includes key players; and the evidence layer includes supporting micro blogs. The temporal properties added into the ontology enable the representation and analysis of the innovation evolvement. We validate our design by examining the type of semantic queries the knowledge base supports, relationship analysis, range analysis, and trend analysis.