汉语句子语义极性分析和观点抽取方法的研究

被引：60

作者：

娄德成

姚天昉

机构：

[1] 上海交通大学计算机科学与工程系

来源：

关键词：

语义极性; 网络评论; 句法分析;

D O I：

暂无

中图分类号：

TP391.1 [文字信息处理];

学科分类号：

摘要：

利用自然语言处理技术,对中文网络评论语句进行语义极性分析和观点抽取。提出了计算词语上下文极性的算法,并且分析主题和修饰成分的匹配关系。最后与手工标注结果进行比较,通过实验证明了该算法的合理性和有效性。

引用

页码：2622 / 2625

页数：4

共 6 条

[1] Towards answering op inion questions: separating facts from op inions and identifying the polarity of op inion sentences. YU H,HATZIVSSILOGLOU V. Proceedings of the 2003 Conference on Emp iricalMethods in Natural Language Processing[C] . 2003
[2] Thumbs up or thumbs down?Semantic orientation applied to unsupervised classification of reviews[A]. TURNEY PD. Proceedings of the Association forComputationalLinguistics 40 th AnniversaryMeeting . 2002
[3] Sentiment m ining in W ebFountain[A]. YI J,NIBLACK W. Proceedings of the 21 st International Conference on Data Engineering(ICDE 2005 ) . 2005
[4] Measuring praise and criticism: inference of semantic orientation from association. TURNEY PD,LITTMAN ML. ACM Transactions on Information System . 2003
[5] Op inion observer: analyzing and comparing op inions on the web. LIU B,HUM. InternationalW orldW ideW eb Conference Comm ittee (IW 3C2 ) . 2005
[6] Polarity classification of celebrity coverage in the Chinese press[A]. TSOU BKY,YUEN RWM. International Conference on Intelligence Analysis . 2005