摘要
为了扩展尽可能多的极性副词(基于词典WordNet 3.0),提出了三种类型的查询字符串。除了Word-Net中的同义关系和反义关系,还使用了近义(similar to)和又见(also see)这两种关系。实验数据表明,后两种关系比前两种关系在扩展极性副词方面更重要。详细的实验验证了所提出的POAE算法加Transform转换函数在自动扩展极性副词方面是可行的。
In order to expand high quality polarity adverbs as many as possible by using WordNet,this paper proposed three types of query string.Besides "synonym" and "antonym" relations,it also used "similar to" and "also see" relations of WordNet.The results of the experiment demonstrate that the last two relations are more important than the first two ones.Extensive experiments show that the combination of POAE algorithm and "Transform" function is very effective for expanding polarity adverb in sentiment analysis.
出处
《计算机应用研究》
CSCD
北大核心
2013年第7期1958-1960,1970,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(61272240)
山东省博士后创新项目专项资金资助项目(201203065)
关键词
情感分析
同义关系
反义关系
近义关系
又见关系
sentiment analysis
synonym relation
antonym relation
similar to relation
also see relation