基于领域本体的在线评论信息层次化挖掘

Hierarchical Mining of Online Reviews Based on Domain Ontology

在线评论作为潜在消费者网购的重要参考依据,挖掘其有价值的信息是有效利用的关键。针对网购平台的设计原则以及消费者的实际需求,融合社会化标注构建领域本体,基于领域本体的层次结构,将在线评论的特征词映射为本体概念,并利用Jess推理引擎提取评论中的隐性产品属性,再将概念间的层次关系映射到产品属性中,构建层次化产品属性集。基于层叠CRFs模型以及情感词典,从在线评论的极性分析到句子级的情感强度分析再到产品属性级的褒贬强度分析,实现在线评论情感倾向性的层次化分析。最后,以手机领域为例,通过四类手机在线评论语料的实验验证基于领域本体的层次化产品属性集挖掘模型以及情感倾向性层次化分析模型的有效性与准确性。

Online reviews as an important reference for potential consumers to online shopping, mining the valuable information is the key to effective use of online reviews. In view of the design principles of online shopping platform and the actual demand of consumers, this paper fused social tagging into construct domain ontology. Based on domain ontology, feature words of online reviews are mapped as ontology concept. And Jess reasoning engine is used to extract the implicit product attributes from reviews. Then this paper constructs the hierarchical product attributes after the hierarchical relationships between concepts are mapped to product attributes. Based on cascading CRFs model and emotional dictionary, the hierarchical analysis of emotional orientation is achieved from the polarity analysis of online reviews to the emotional intensity analysis of sentence level to the appraisement intensity analysis of product attribute level. Finally, using mobile phone as an example, this paper verifies the effectiveness and accuracy of hierarchical mining model of product attribute and hierarchical analysis model of emotional orientation based on domain ontology by the experiments that use online reviews corpora of four types of mobile phone.