def single_review_sentiment_score(weibo_sent):
single_review_senti_score = []
cuted_review = tp.cut_sentence(weibo_sent) # 句子切分，单独对每个句子进行分析
for sent in cuted_review:
seg_sent = tp.segmentation(sent) # 分词
seg_sent = tp.del_stopwords(seg_sent)[:]
#for w in seg_sent:
# print w,
i = 0 # 记录扫描到的词的位置
s = 0 # 记录情感词的位置
poscount = 0 # 记录该分句中的积极情感得分
negcount = 0 # 记录该分句中的消极情感得分
for word in seg_sent: # 逐词分析
#print word
if word in posdict: # 如果是积极情感词
#print "posword:", word
poscount += 1 # 积极得分+1
for w in seg_sent[s:i]:
poscount = match(w, poscount)
#print "poscount:", poscount
s = i + 1 # 记录情感词的位置变化
elif word in negdict: # 如果是消极情感词
#print "negword:", word
negcount += 1
for w in seg_sent[s:i]:
negcount = match(w, negcount)
#print "negcount:", negcount
s = i + 1
# 如果是感叹号，表示已经到本句句尾
elif word == "！".decode("utf-8") or word == "!".decode('utf-8'):
for w2 in seg_sent[::-1]: # 倒序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:
poscount += 2
break
elif w2 in negdict:
negcount += 2
break
i += 1
#print "poscount,negcount", poscount, negcount
single_review_senti_score.append(
transform_to_positive_num(poscount, negcount)) # 对得分做最后处理
pos_result, neg_result = 0, 0 # 分别记录积极情感总得分和消极情感总得分
for res1, res2 in single_review_senti_score: # 每个分句循环累加
pos_result += res1
neg_result += res2
#print pos_result, neg_result
result = pos_result - neg_result # 该条微博情感的最终得分
result = round(result, 1)
return result
def mysentiment_score_list(oneblog):
cuted_data = []
for sen in tp.cut_sentence(oneblog):
cuted_data.append(sen)
blog_score_list = []
for sent in cuted_data: #循环遍历评论中的每一个分句
segtmp = tp.segmentation(sent)
#print segtmp
pos_count = 0
neg_count = 0
for word in segtmp:
if word in posdict:
pos_count += 1
elif word in negdict:
neg_count += 1
blog_score_list.append([pos_count, neg_count])
return blog_score_list
def mysentiment_score_list(oneblog):
cuted_data = []
for sen in tp.cut_sentence(oneblog):
cuted_data.append(sen)
blog_score_list = []
for sent in cuted_data: #循环遍历评论中的每一个分句
segtmp = tp.segmentation(sent)
#print segtmp
pos_count = 0
neg_count = 0
for word in segtmp:
if word in posdict:
pos_count +=1
elif word in negdict:
neg_count +=1
blog_score_list.append([pos_count,neg_count])
return blog_score_list
def sentiment_score_list(oneblog):
cuted_data = []
for sen in tp.cut_sentence(oneblog):
#print sen
cuted_data.append(sen)
#print 'testing..............'
count1 = []
count2 = []
#for sents in cuted_data: #循环遍历每一个评论
for sent in cuted_data: #循环遍历评论中的每一个分句
segtmp = tp.segmentation(sent) #把句子进行分词，以列表的形式返回
#segtmp =list(set(segtmp)) #去除用于的词，如果情感词出现多次，那么会被重复计算
#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 = 0
negcount2 = 0
negcount3 = 0
for word in segtmp:
#print word,type(word),'testing...........'
if word in posdict: #判断词语是否是情感词
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 /= 2.0
elif w in insufficientdict:
poscount /= 4.0
elif w in inversedict:
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 #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 += 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 /= 2.0
elif w in insufficientdict:
negcount /= 4.0
elif w in inversedict:
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 == '！'.decode('utf8') or word == '!'.decode(
'utf8'): ##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 += 2
negcount3 += 2
break
i += 1 #扫描词位置前移
#print pos_count,neg_count,'testing...................'
#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 = -poscount3
pos_count = -negcount3
else:
pos_count = poscount3
neg_count = negcount3
count1.append([pos_count, neg_count])
count2.append(count1)
count1 = []
return count2
def sentiment_score_list(oneblog):
cuted_data = []
for sen in tp.cut_sentence(oneblog):
#print sen
cuted_data.append(sen)
#print 'testing..............'
count1 = []
count2 = []
#for sents in cuted_data: #循环遍历每一个评论
for sent in cuted_data: #循环遍历评论中的每一个分句
segtmp = tp.segmentation(sent) #把句子进行分词，以列表的形式返回
#segtmp =list(set(segtmp)) #去除用于的词，如果情感词出现多次，那么会被重复计算
#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 = 0
negcount2 = 0
negcount3 = 0
for word in segtmp:
#print word,type(word),'testing...........'
if word in posdict: #判断词语是否是情感词
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 /= 2.0
elif w in insufficientdict:
poscount /= 4.0
elif w in inversedict:
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 #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 += 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 /= 2.0
elif w in insufficientdict:
negcount /= 4.0
elif w in inversedict:
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 == '！'.decode('utf8') or word == '!'.decode('utf8'): ##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 += 2
negcount3 += 2
break
i += 1 #扫描词位置前移
#print pos_count,neg_count,'testing...................'
#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 = -poscount3
pos_count = -negcount3
else:
pos_count = poscount3
neg_count = negcount3
count1.append([pos_count, neg_count])
count2.append(count1)
count1 = []
return count2