TextAnalysis
所属分类:Windows编程
开发工具:Visual C++
文件大小:13328KB
下载次数:12
上传日期:2014-03-13 22:16:24
上 传 者:
970054507
说明: TextAnalysis系统及算法设计
输入为ICTCLAS分词后的词语结构信息,对每个词语的词性进行判断。
1. 如果不存在词性,则跳过这次循环。用来跳过一些语气助词等无意义的信息。
2. 由于每个句子都有几个子句,而每个子句都是一个独立的主谓宾结构,所以系统将子句通过标点符号来分隔。最后将所以子句的总情感权值相加得到总句的情感权值。
3. 在对字典的预处理阶段,系统对不同程度的词语赋予了不同的权值。为了提高处理程序的效率,系统只分析对体现语言情感有较大作用的词性(包括形容词、副词、动词、名词、数词)。
4. 对于副词,需要特殊处理。首先副词是加强语气的作用,如“非常好”,“非常糟糕”。此时句子的情感权值就需要用到副词乘以原来的权值。另外,如“非常非常的不好”,这是就需要用副词来乘以副词了。对应函数sentenceAnalysis。
5. 对于字典中词语权值的说明。对于否定词语,系统设置为-1,即与原来的权值相反,这样也满足双重或多重否定的要求。对于不同的程度词语,对应的分为6个层次,分别赋予不同的权值,以表示不同语气的情感权值的强弱。对于褒义词和贬义词,系统简单的赋予1和-1的权值。对应函数sentenceAnalysis。
(Enter the configuration information for the word after word ICTCLAS , judge for the part of speech of each word .
1 If there is no speech , skip this cycle. Used to skip some of the modal particle and other meaningless information .
2 Since each sentence has several clauses , each clause is a separate subject-verb-object structure , so the system will be separated by punctuation clause . Finally, it is the emotional weight of the total obtained by adding the clause emotional value of the total sentence .
3 in the dictionary for the pretreatment phase, the system for different levels of words given a different weight . In order to improve the efficiency of the process , the system only analyzes the emotional language to reflect the greater role of speech ( including adjectives, adverbs , verbs , nouns , numerals ) .
4 For adverbs , require special handling. First, the adverb is to strengthen the role of tone , such as " very good" , "very bad ." At this point the emotional weight of)
文件列表:
TextAnalysis\Debug\TextAnalysis.exe (221184, 2013-11-21)
TextAnalysis\Debug\TextAnalysis.exp (907, 2013-11-21)
TextAnalysis\Debug\TextAnalysis.ilk (1010488, 2013-11-21)
TextAnalysis\Debug\TextAnalysis.lib (2178, 2013-11-21)
TextAnalysis\Debug\TextAnalysis.pdb (1649664, 2013-11-21)
TextAnalysis\ipch\textanalysis-511e494c\textanalysis-c51ddaf5.ipch (2752512, 2013-11-21)
TextAnalysis\TextAnalysis\20131121.err (6820, 2013-11-21)
TextAnalysis\TextAnalysis\configure.xml (874, 2013-11-21)
TextAnalysis\TextAnalysis\Data\BIG2GBK.map (286196, 2012-05-18)
TextAnalysis\TextAnalysis\Data\BIG5.pdat (468456, 2012-05-18)
TextAnalysis\TextAnalysis\Data\BIG5.wordlist (158695, 2012-05-18)
TextAnalysis\TextAnalysis\Data\BiWord.big (3520144, 2009-01-16)
TextAnalysis\TextAnalysis\Data\charset.type (65540, 2012-11-08)
TextAnalysis\TextAnalysis\Data\Configure.xml (856, 2012-11-14)
TextAnalysis\TextAnalysis\Data\CoreDict.pdat (1696620, 2009-01-16)
TextAnalysis\TextAnalysis\Data\CoreDict.pos (1786424, 2009-01-16)
TextAnalysis\TextAnalysis\Data\CoreDict.unig (478168, 2009-01-16)
TextAnalysis\TextAnalysis\Data\FieldDict.pdat (262236, 2009-01-16)
TextAnalysis\TextAnalysis\Data\FieldDict.pos (72, 2009-01-16)
TextAnalysis\TextAnalysis\Data\GBK.pdat (549204, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBK.wordlist (166985, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBK2BIG.map (286196, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBK2GBKC.map (286196, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBK2UTF.map (286196, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBKA.pdat (550848, 2012-12-22)
TextAnalysis\TextAnalysis\Data\GBKA.wordlist (166985, 2012-12-22)
TextAnalysis\TextAnalysis\Data\GBKA2UTF.map (286196, 2012-12-22)
TextAnalysis\TextAnalysis\Data\GBKC.pdat (550848, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBKC.wordlist (166985, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GBKC2GBK.map (286196, 2012-05-18)
TextAnalysis\TextAnalysis\Data\GranDict.pdat (1978128, 2009-01-16)
TextAnalysis\TextAnalysis\Data\GranDict.pos (1778776, 2009-01-16)
TextAnalysis\TextAnalysis\Data\ICTPOS.map (406, 2009-01-16)
TextAnalysis\TextAnalysis\Data\NewWord.lst (126, 2012-12-22)
TextAnalysis\TextAnalysis\Data\NLPIR.ctx (37253, 2009-01-16)
TextAnalysis\TextAnalysis\Data\NLPIR.user (3356, 2013-11-15)
TextAnalysis\TextAnalysis\Data\NLPIR_First.map (288, 2009-01-16)
TextAnalysis\TextAnalysis\Data\nr.ctx (2213, 2009-01-16)
TextAnalysis\TextAnalysis\Data\nr.fsa (3008, 2009-01-16)
TextAnalysis\TextAnalysis\Data\nr.role (1757200, 2009-01-16)
... ...
========================================================================
控制台应用程序:TextAnalysis 项目概述
========================================================================
应用程序向导已为您创建了此 TextAnalysis 应用程序。
本文件概要介绍组成 TextAnalysis 应用程序的每个文件的内容。
TextAnalysis.vcxproj
这是使用应用程序向导生成的 VC++ 项目的主项目文件,
其中包含生成该文件的 Visual C++
的版本信息,以及有关使用应用程序向导选择的平台、配置和项目功能的信息。
TextAnalysis.vcxproj.filters
这是使用“应用程序向导”生成的 VC++ 项目筛选器文件。
它包含有关项目文件与筛选器之间的关联信息。 在 IDE
中,通过这种关联,在特定节点下以分组形式显示具有相似扩展名的文件。
例如,“.cpp”文件与“源文件”筛选器关联。
TextAnalysis.cpp
这是主应用程序源文件。
/////////////////////////////////////////////////////////////////////////////
其他标准文件:
StdAfx.h,StdAfx.cpp
这些文件用于生成名为 TextAnalysis.pch 的预编译头 (PCH) 文件和
名为 StdAfx.obj 的预编译类型文件。
/////////////////////////////////////////////////////////////////////////////
其他注释:
应用程序向导使用“TODO:”注释来指示应添加或自定义的源代码部分。
/////////////////////////////////////////////////////////////////////////////
近期下载者:
相关文件:
收藏者: