机器学习算法Python实现：基于情感词典的文本情感分析

# -*- coding:utf-8 -* #本代码是在jupyter notebook上实现，author:huzhifei， create
time:2018/8/14 #本脚本主要实现了基于python通过已有的情感词典对文本数据做的情感分析的项目目的
#导入对应的包及相关的自定义的jieba词典 import jieba import numpy as np
jieba.load_userdict("C:\\Users\\Desktop\\中文分词词库整理\\中文分词词库整理\\百度分词词库.txt") #
打开词典文件，返回列表 def open_dict(Dict='hahah',path =
'C:\\Users\\Desktop\\Textming\\'): path = path + '%s.txt' %Dict dictionary =
open(path, 'r', encoding='utf-8',errors='ignore') dict = [] for word in
dictionary: word = word.strip('\n') dict.append(word) return dict def
judgeodd(num): #往情感词前查找否定词，找完全部否定词，若数量为奇数，乘以-1，若数量为偶数，乘以1. if num % 2 == 0:
return 'even' else: return 'odd' deny_word = open_dict(Dict='deny')#否定词词典
posdict = open_dict(Dict='positive')#积极情感词典 negdict = open_dict(Dict =
'negative')#消极情感词典 degree_word = open_dict(Dict =
'degree',path='C:\\Users\\AAS-1413\\Desktop\\Textming\\')#程度词词典 #为程度词设置权重
mostdict = degree_word[degree_word.index('extreme')+1:
degree_word.index('very')] #权重4，即在情感前乘以3 verydict =
degree_word[degree_word.index('very')+1: degree_word.index('more')] #权重3
moredict = degree_word[degree_word.index('more')+1:
degree_word.index('ish')]#权重2 ishdict = degree_word[degree_word.index('ish')+1:
degree_word.index('last')]#权重0.5 seg_sentence=[] def
sentiment_score_list(data): for i in data: seg_sentence.append(i.replace('
','，'))#去除逗号后的评论数据集 #seg_sentence=data.replace(' ','，').split(',')#以逗号分隔 count1
= [] count2 = [] for sen in seg_sentence: #print(sen)# 循环遍历每一个评论 segtmp =
jieba.lcut(sen, cut_all=False) # 把句子进行分词，以列表的形式返回 #print(segtmp) i = 0
#记录扫描到的词的位置 a = 0 #记录情感词的位置 poscount = 0 # 积极词的第一次分值 poscount2 = 0 # 积极反转后的分值
poscount3 = 0 # 积极词的最后分值（包括叹号的分值） negcount = 0 negcount2 = 0 negcount3 = 0 for
word in segtmp: if word in posdict: # 判断词语是否是积极情感词 poscount +=1 c = 0 for w in
segtmp[a:i]: # 扫描情感词前的程度词 if w in mostdict: poscount *= 4.0 elif w in verydict:
poscount *= 3.0 elif w in moredict: poscount *= 2.0 elif w in ishdict: poscount
*= 0.5 elif w in deny_word: c+= 1 if judgeodd(c) == 'odd': # 扫描情感词前的否定词数
poscount *= -1.0 poscount2 += poscount poscount = 0 poscount3 = poscount +
poscount2 + poscount3 poscount2 = 0 else: poscount3 = poscount + poscount2 +
poscount3 poscount = 0 a = i+1 elif word in negdict: # 消极情感的分析，与上面一致 negcount
+= 1 d = 0 for w in segtmp[a:i]: if w in mostdict: negcount *= 4.0 elif w in
verydict: negcount *= 3.0 elif w in moredict: negcount *= 2.0 elif w in
ishdict: negcount *= 0.5 elif w in degree_word: d += 1 if judgeodd(d) == 'odd':
negcount *= -1.0 negcount2 += negcount negcount = 0 negcount3 = negcount +
negcount2 + negcount3 negcount2 = 0 else: negcount3 = negcount + negcount2 +
negcount3 negcount = 0 a = i + 1 elif word == '！' or word == '!': # 判断句子是否有感叹号
for w2 in segtmp[::-1]: # 扫描感叹号前的情感词，发现后权值+2，然后退出循环 if w2 in posdict: poscount3
+= 2 elif w2 in negdict: negcount3 += 2 else: poscount3 +=0 negcount3 +=0 break
else: poscount3=0 negcount3=0 i += 1 # 以下是防止出现负数的情况 pos_count = 0 neg_count = 0
if poscount3 <0 and negcount3 > 0: neg_count += negcount3 - poscount3 pos_count
= 0 elif negcount3 <0 and poscount3 > 0: pos_count = poscount3 - negcount3
neg_count = 0 elif poscount3 <0 and negcount3 < 0: neg_count = -pos_count
pos_count = -neg_count else: pos_count = poscount3 neg_count = negcount3
count1.append([pos_count,neg_count]) #返回每条评论打分后的列表 #print(count1)
count2.append(count1) count1=[] #print(count2) return count2 #返回所有评论打分后的列表 def
sentiment_score(senti_score_list):#分析完所有评论后，正式对每句评论打情感分 #score = [] s='' w=''
for review in senti_score_list:#senti_score_list #print(review) score_array =
np.array(review) #print(score_array) Pos = np.sum(score_array[:,0])#积极总分 Neg =
np.sum(score_array[:,1])#消极总分 AvgPos = np.mean(score_array[:,0])#积极情感均值 AvgPos
= float('%.lf' % AvgPos) AvgNeg = np.mean(score_array[:, 1])#消极情感均值 AvgNeg =
float('%.1f' % AvgNeg) StdPos = np.std(score_array[:, 0])#积极情感方差 StdPos =
float('%.1f' % StdPos) StdNeg = np.std(score_array[:, 1])#消极情感方差 StdNeg =
float('%.1f' % StdNeg) #s+=([Pos,Neg,AvgPos,AvgNeg,StdPos,StdNeg]))
s+='\n'+str([Pos, Neg]) #score.append([Pos,Neg]) res=Pos-Neg if res>0:
w+='\n'+'好评' print ('该条评论是：好评') elif res<0: w+='\n'+'差评' print ('该条评论是：差评')
else: w+='\n'+'中评' print ('该条评论是：中评') #print(w) return w #读取要做情感分析的文本
data=open("content.txt","r",errors='ignore') #调用函数做实体分析
sentiment_score(sentiment_score_list(data)) #将函数返回结果存入txt中
f=open('s.txt','w',errors='ignore')
f.write(sentiment_score(sentiment_score_list(data))) f.close()

• « 上一篇：K-近邻法（KNN算法）
• » 下一篇：上周热点回顾（2.18-2.24）