基于中文知识的半自动复杂感性分类与本体构建

In order to recognize one's intention from the communication, both the meaning and the emotion are necessary to be interpreted correctly. But until now the study of fine-grained theory of emotion is still full of challenges. This paper analyzes emotion category according to the statistics of Affective Word (AW) hierarchy and describes an emotion ontology from Chinese knowledge resource semiautomatically created for human machine interaction. The emotion hierarchy is called complex emotion. Firstly, over 7000 AWs have been annotated and their detailed explanations had been collected for an affective lexicon and then the consistent relationships are automatically parsed and a serial of emotion hierarchical structures are built up. More than 50 affective categories are extracted by a lexical clustering algorithm and about 5000 nouns and adjectives and 2000 verbs are categorized into the predicate hierarchy. The results have been evaluated to be valid by two metrics.