用WordNet实现中文情感分析

56 阅读 0 评论 37 点赞

我是靠谱客的博主霸气翅膀，最近开发中收集的这篇文章主要介绍用WordNet实现中文情感分析，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

1. 分析

中文的情感分析可以用词林做，词林有一大类（Ｇ类）对应心理活动，但是相对于wordnet还是太简单了．因此使用nltk+wordnet的方案，如下：

1) 中文分词：结巴分词

2) 中英文翻译：wordnet汉语开放词网，可从以下网址下载：
http://compling.hss.ntu.edu.sg/cow/

3) 情感分析：wordnet的sentiwordnet组件

4) 停用词：参考以下网页，另外加入常用标点符号
http://blog.csdn.net/u010533386/article/details/51458591

2. 代码

# encoding=utf-8
import jieba
import sys
import codecs

reload(sys)

import nltk
from nltk.corpus import wordnet as wn
from nltk.corpus import sentiwordnet as swn

sys.setdefaultencoding('utf8')

def doSeg(filename) :
    f = open(filename, 'r+')
    file_list = f.read()
    f.close()

    seg_list = jieba.cut(file_list)

    stopwords = []  
    for word in open("./stop_words.txt", "r"):  
        stopwords.append(word.strip()) 

    ll = []
    for seg in seg_list :
        if (seg.encode("utf-8") not in stopwords and seg != ' ' and seg != '' and seg != "n" and seg != "nn"):
            ll.append(seg)
    return ll

def loadWordNet():
    f = codecs.open("./cow-not-full.txt", "rb", "utf-8")
    known = set()
    for l in f:
        if l.startswith('#') or not l.strip():
            continue
        row = l.strip().split("t")
        if len(row) == 3:
            (synset, lemma, status) = row 
        elif len(row) == 2:
            (synset, lemma) = row 
            status = 'Y'
        else:
            print "illformed line: ", l.strip()
        if status in ['Y', 'O' ]:
            if not (synset.strip(), lemma.strip()) in known:
                known.add((synset.strip(), lemma.strip()))
    return known

def findWordNet(known, key):
    ll = [];
    for kk in known:
        if (kk[1] == key):
             ll.append(kk[0])
    return ll

def id2ss(ID):
    return wn._synset_from_pos_and_offset(str(ID[-1:]), int(ID[:8]))

def getSenti(word):
    return swn.senti_synset(word.name())

if __name__ == '__main__' :
    known = loadWordNet()
    words = doSeg(sys.argv[1])

    n = 0
    p = 0
    for word in words:
      ll = findWordNet(known, word)
      if (len(ll) != 0):
          n1 = 0.0
          p1 = 0.0
          for wid in ll:
              desc = id2ss(wid)
              swninfo = getSenti(desc)
              p1 = p1 + swninfo.pos_score()
              n1 = n1 + swninfo.neg_score()
          if (p1 != 0.0 or n1 != 0.0):
              print word, '-> n ', (n1 / len(ll)), ", p ", (p1 / len(ll))
          p = p + p1 / len(ll)
          n = n + n1 / len(ll)
    print "n", n, ", p", p