NLP之情感分析：基于python编程(jieba库)实现中文文本情感分析(得到的是情感评分)之全部代码
目录
全部代码
相关文章
NLP之情感分析：基于python编程(jieba库)实现中文文本情感分析(得到的是情感评分)
NLP之情感分析：基于python编程(jieba库)实现中文文本情感分析(得到的是情感评分)之全部代码
全部代码
# coding:utf-8import jiebaimport numpy as np#打开词典文件，返回列表def open_dict(Dict = 'hahah', path=r'data/Textming'):path = path + '%s.txt' % Dictdictionary = open(path, 'r', encoding='utf-8')dict = []for word in dictionary:word = word.strip('\n')dict.append(word)return dictdef judgeodd(num):if (num % 2) == 0:return 'even'else:return 'odd'#注意，这里你要修改path路径。deny_word = open_dict(Dict = '否定词', path= r'F:/File_Python/Resources/data/Textming/')posdict = open_dict(Dict = 'positive', path= r'F:/File_Python/Resources/data/Textming/')negdict = open_dict(Dict = 'negative', path= r'F:/File_Python/Resources/data/Textming/')degree_word = open_dict(Dict = '程度级别词语', path= r'F:/File_Python/Resources/data/Textming/')mostdict = degree_word[degree_word.index('extreme')+1 : degree_word.index('very')]#权重4，即在情感词前乘以4verydict = degree_word[degree_word.index('very')+1 : degree_word.index('more')]#权重3moredict = degree_word[degree_word.index('more')+1 : degree_word.index('ish')]#权重2ishdict = degree_word[degree_word.index('ish')+1 : degree_word.index('last')]#权重0.5def sentiment_score_list(dataset):seg_sentence = dataset.split('。')count1 = []count2 = []for sen in seg_sentence: #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 #积极词反转后的分值poscount3 = 0 #积极词的最后分值（包括叹号的分值）negcount = 0negcount2 = 0negcount3 = 0for word in segtmp:if word in posdict: # 判断词语是否是情感词poscount += 1c = 0for w in segtmp[a:i]: # 扫描情感词前的程度词if w in mostdict:poscount *= 4.0elif w in verydict:poscount *= 3.0elif w in moredict:poscount *= 2.0elif w in ishdict:poscount *= 0.5elif w in deny_word:c += 1if judgeodd(c) == 'odd': # 扫描情感词前的否定词数poscount *= -1.0poscount2 += poscountposcount = 0poscount3 = poscount + poscount2 + poscount3poscount2 = 0else:poscount3 = poscount + poscount2 + poscount3poscount = 0a = i + 1 # 情感词的位置变化elif word in negdict: # 消极情感的分析，与上面一致negcount += 1d = 0for w in segtmp[a:i]:if w in mostdict:negcount *= 4.0elif w in verydict:negcount *= 3.0elif w in moredict:negcount *= 2.0elif w in ishdict:negcount *= 0.5elif w in degree_word:d += 1if judgeodd(d) == 'odd':negcount *= -1.0negcount2 += negcountnegcount = 0negcount3 = negcount + negcount2 + negcount3negcount2 = 0else:negcount3 = negcount + negcount2 + negcount3negcount = 0a = i + 1elif 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 or negdict:poscount3 += 2negcount3 += 2breaki += 1 # 扫描词位置前移# 以下是防止出现负数的情况pos_count = 0neg_count = 0if poscount3 < 0 and negcount3 > 0:neg_count += negcount3 - poscount3pos_count = 0elif negcount3 < 0 and poscount3 > 0:pos_count = poscount3 - negcount3neg_count = 0elif poscount3 < 0 and negcount3 < 0:neg_count = -poscount3pos_count = -negcount3else:pos_count = poscount3neg_count = negcount3count1.append([pos_count, neg_count])count2.append(count1)count1 = []return count2def sentiment_score(senti_score_list):score = []for review in senti_score_list:score_array = np.array(review)Pos = np.sum(score_array[:, 0])Neg = np.sum(score_array[:, 1])AvgPos = np.mean(score_array[:, 0])AvgPos = float('%.1f'%AvgPos)AvgNeg = np.mean(score_array[:, 1])AvgNeg = float('%.1f'%AvgNeg)StdPos = np.std(score_array[:, 0])StdPos = float('%.1f'%StdPos)StdNeg = np.std(score_array[:, 1])StdNeg = float('%.1f'%StdNeg)score.append([Pos, Neg, AvgPos, AvgNeg, StdPos, StdNeg]) #积极、消极情感值总和(最重要)，积极、消极情感均值，积极、消极情感方差。return scoredef EmotionByScore(data):result_list=sentiment_score(sentiment_score_list(data))return result_list[0][0],result_list[0][1]def JudgingEmotionByScore(Pos, Neg):if Pos > Neg:str='1'elif Pos < Neg:str='-1'elif Pos == Neg:str='0'return strdata1= '今天上海的天气真好！我的心情非常高兴！如果去旅游的话我会非常兴奋！和你一起去旅游我会更加幸福！'data2= '救命，你是个坏人，救命，你不要碰我，救命，你个大坏蛋！'data3= '美国华裔科学家,祖籍江苏扬州市高邮县,生于上海,斯坦福大学物理系,电子工程系和应用物理系终身教授!'print(sentiment_score(sentiment_score_list(data1)))print(sentiment_score(sentiment_score_list(data2)))print(sentiment_score(sentiment_score_list(data3)))a,b=EmotionByScore(data1)emotion=JudgingEmotionByScore(a,b)print(emotion)
