|
NRC词典的加载方法和分词方法之前的文章有写，直接套用即可。
具体函数参考了这篇文章：基于情感词典的文本情感分析(附代码)_Petrichoryi的博客-CSDN博客_bosonnlp情感词典
我相当于是把这篇文章里的正负情感改成了NRC词典中的八种离散情感，进行逐一计算，具体代码如下：
not_word_file = open('E:/data/否定词.txt','r+',encoding='utf-8')
not_word_list = not_word_file.readlines()
not_word_list = [w.strip() for w in not_word_list]
#读取程度副词文件，里面包含表示程度副词程度的数字
degree_file = open('E:/data/程度副词.txt','r+',encoding='utf-8')
degree_list = degree_file.readlines()
degree_list = [item.strip().split(',') for item in degree_list]
print(not_word_list)
print(degree_list)
from collections import defaultdict
def classify_words(word_list,Sentiment):
sen_dict = defaultdict()
for i in Sentiment:
sen_dict[i] = 1 #因为用的是NRC词典中的情感词汇，没有具体的情感程度，都定为1
degree_dict = defaultdict()
for i in degree_list:
degree_dict[i[0]] = i[1]
sen_word = dict()
not_word = dict()
degree_word = dict()
#分类
for i in range(len(word_list)):
word = word_list[i]
if word in sen_dict.keys() and word not in not_word_list and word not in degree_dict.keys():
# 找出分词结果中在情感字典中的词
sen_word[i] = sen_dict[word]
elif word in not_word_list and word not in degree_dict.keys():
# 分词结果中在否定词列表中的词
not_word[i] = -1
elif word in degree_dict.keys():
# 分词结果中在程度副词中的词
degree_word[i] = degree_dict[word]
return sen_word,not_word,degree_word
def score_sentiment(sen_word,not_word,degree_word,seg_result):
#权重初始化为1
W = 1
score = 0
#情感词下标初始化
sentiment_index = -1
#情感词的位置下标集合
sentiment_index_list = list(sen_word.keys())
#遍历分词结果
for i in range(0,len(seg_result)):
#如果是情感词
if i in sen_word.keys():
#权重*情感词得分
score += W*float(sen_word[i])
#情感词下标加一，获取下一个情感词的位置
sentiment_index += 1
if sentiment_index < len(sentiment_index_list)-1:
#判断当前的情感词与下一个情感词之间是否有程度副词或否定词
for j in range(sentiment_index_list[sentiment_index],sentiment_index_list[sentiment_index+1]):
#更新权重，如果有否定词，权重取反
if j in not_word.keys():
W = W*(-1)
elif j in degree_word.keys():
W *= float(degree_word[j])
#定位到下一个情感词
if sentiment_index < len(sentiment_index_list)-1:
i = sentiment_index_list[sentiment_index+1]
return score
def sentiment_score(sentence,Sentiment):
#1.对文档分词
seg_list = seg_depart(sentence) #分词函数之前文章有写
#2.将分词结果转换成字典，找出情感词、否定词和程度副词
sen_word,not_word,degree_word = classify_words(seg_list,Sentiment)
#3.计算得分
score = score_sentiment(sen_word,not_word,degree_word,seg_list)
return score
#将NRC词典中所有离散情感词汇整理成二维列表
Senti_list8 = [Anger,Anticipation,Disgust,Fear,Joy,Sadness,Surprise,Trust]
#将文档中句子的八种情绪结果转换为字典
all_senti = dict()
i = 0
for senti in Senti_list8:
filename = r'E:\data\test1.csv'
senti_count = []
with open(filename, 'r', encoding='UTF-8') as csvfile:
next(csvfile)
reader = csv.reader(csvfile)
for row in reader:
score = sentiment_score(row[0],Sentiment=senti)
senti_count.append(score)
print(senti_count)
all_senti[i]=senti_count
i = i+1
#存为csv
test = pd.DataFrame.from_dict(all_senti)
test.to_csv(r"E:\data\test1_result2.csv")
|