基于地名识别的地方新闻分类方法  

A Classification Method of Local News Based on Place Name Recognition

作　　者：李果 刘任任[1] LI Guo;LIU Ren-ren(College of Information Engineering,Xiangtan University,Xiangtan,Hunan 410075,China;College of Computer Science and Technology,Hunan University of Arts and Science,Changde,Hunan 415000,China)

机构地区：[1]湘潭大学信息工程学院,湖南湘潭411105 [2]湖南文理学院计算机科学与技术学院,湖南常德415000

出　　处：《软件》2018年第4期73-76,共4页Software

基　　金：湖南文理学院2016年校级科研项目(项目编号:16YB17)

摘　　要：地方新闻时常因为传播渠道窄而被忽视,但在特定范围内具有较高的价值。新闻文本中有很多地理空间信息,本文提出了一种基于地名识别的地方新闻分类方法,首先建立地名词典,利用中文分词、地名识别技术将原始文本转换为地名词汇集,然后利用地名标准化、地名消歧技术进一步精简地名词汇集,最后通过规则匹配实现新闻文本的行政区划归类。实验结果表明,该方法对于地方新闻文本分类具有较高的准确率和召回率。Local news is often neglected because of the narrow channel of communication, but it is of high value in a certain range. There are a lot of geospatial information in news texts, this paper proposes a classification method of local news based on place name recognition, firstly, establish a toponym library, convert the original text into a place name set by using Chinese segmentation, name recognition technology, then use the standardization of geographical names, geographical names disambiguation technology to streamline the place name set, finally the rule matching is used to complete the classification of the news text. The experimental result shows that the method has high accuracy and recall rate for local news text classification.

关 键 词：地名识别 地方新闻 文本分类 中文信息处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]