python新闻情感分析_对知乎数据进行情感分析

关于编码问题：‘utf-8’ codec can’t decode byte 0xb7 in position 0: invalid start byte参见这篇博文：https://www.cnblogs.com/xiaolan-Lin/p/11653432.html

代码来自于这篇博文：https://blog.csdn.net/lom9357bye/article/details/79058946?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522158937528619724839264541%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fall.57674%2522%257D&request_id=158937528619724839264541&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2allfirst_rank_v2~rank_v25-2-79058946.nonecase&utm_term=%E5%9F%BA%E4%BA%8E%E6%83%85%E6%84%9F%E8%AF%8D%E5%85%B8

程度词要自己标注权重，可以把txt的文件复制到excel，新建一行再自动填充：

词典数据来自于这里：https://download.csdn.net/download/siyanyu/9880970

网上找代下下载的词典，需要的话可以点击网盘：链接：https://pan.baidu.com/s/1oVXtjtD9pTLP5Y277He-IQ

提取码：6h98

最后附上代码：

# -*- coding: utf-8 -*-

"""

Created on Wed May 13 21:10:58 2020

1、情感词典：BosonNLP情感词典是从微博、新闻、论坛等数据来源的上百万篇情感标注数据当中

自动构建的情感极性词典。因为标注包括微博数据，该词典囊括了很多网络用语及非正式简称，

对非规范文本也有较高的覆盖率。该情感词典可以用于构建社交媒体情感分析引擎，负面内容发现等应用。

2、停用词

3、否定词

4、程度副词

@author: 谢蕾

"""

from collections import defaultdict

import os

import re

import jieba

import codecs

import xlrd

import datetime

from xlrd import xldate_as_tuple

from openpyxl import Workbook

def handle_date(date):

tuple = xldate_as_tuple(date, 0)

# print(tuple)

# excel_datetime=datetime.datetime(*tuple)

# print(excel_datetime)

return tuple

def seg_word(sentence):

"""使用jieba对文档分词"""

seg_list = jieba.cut(sentence)

seg_result = []

for w in seg_list:

seg_result.append(w)

# 读取停用词文件

stopwords = set()

fr = codecs.open('停用词.txt', 'r', 'utf-8')

for word in fr:

stopwords.add(word.strip())

fr.close()

# 去除停用词

return list(filter(lambda x: x not in stopwords, seg_result))

def classify_words(word_dict):

"""词语分类,找出情感词、否定词、程度副词"""

# 读取情感字典文件

sen_file = open('情感词1.0.txt', 'r+', encoding='utf-8')

# 获取字典文件内容

sen_list = sen_file.readlines()

# 创建情感字典

sen_dict = defaultdict()

# 读取字典文件每一行内容，将其转换为字典对象，key为情感词，value为对应的分值

for s in sen_list:

# 每一行内容根据空格分割，索引0是情感词，索引1是情感分值

sen_dict[s.split(' ')[0]] = s.split(' ')[1]

# 读取否定词文件

not_word_file = open('否定词.txt', 'r+', encoding='unicode_escape')

# 由于否定词只有词，没有分值，使用list即可

not_word_list = not_word_file.readlines()

# 读取程度副词文件

degree_file = open('程度词.txt', 'r+', encoding='utf-8')

degree_list = degree_file.readlines()

degree_dic = defaultdict()

# 程度副词与情感词处理方式一样，转为程度副词字典对象，key为程度副词，value为对应的程度值

for d in degree_list:

degree_dic[d.split(',')[0]] = d.split(',')[1]

# 分类结果，词语的index作为key,词语的分值作为value，否定词分值设为-1

sen_word = dict()

not_word = dict()

degree_word = dict()

# 分类

for word in word_dict.keys():

if word in sen_dict.keys() and word not in not_word_list and word not in degree_dic.keys():

# 找出分词结果中在情感字典中的词

sen_word[word_dict[word]] = sen_dict[word]

elif word in not_word_list and word not in degree_dic.keys():

# 分词结果中在否定词列表中的词

not_word[word_dict[word]] = -1

elif word in degree_dic.keys():

# 分词结果中在程度副词中的词

degree_word[word_dict[word]] = degree_dic[word]

sen_file.close()

degree_file.close()

not_word_file.close()

# 将分类结果返回

return sen_word, not_word, degree_word

def list_to_dict(word_list):

"""将分词后的列表转为字典，key为单词，value为单词在列表中的索引，索引相当于词语在文档中出现的位置"""

data = {}

for x in range(0, len(word_list)):

data[word_list[x]] = x

return data

def get_init_weight(sen_word, not_word, degree_word):

# 权重初始化为1

W = 1

# 将情感字典的key转为list

sen_word_index_list = list(sen_word.keys())

if len(sen_word_index_list) == 0:

return W

# 获取第一个情感词的下标，遍历从0到此位置之间的所有词，找出程度词和否定词

for i in range(0, sen_word_index_list[0]):

if i in not_word.keys():

W *= -1

elif i in degree_word.keys():

# 更新权重，如果有程度副词，分值乘以程度副词的程度分值

W *= float(degree_word[i])

return W

def socre_sentiment(sen_word, not_word, degree_word, seg_result):

"""计算得分"""

# 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(遍历分词结果是为了定位两个情感词之间的程度副词和否定词)

for i in range(0, len(seg_result)):

# 若是程度副词

if i in degree_word.keys():

W*=degree_word[i]

# 若是否定词

elif i in not_word.keys():

# print(i)

W*=-1

elif i in sen_word.keys():

score+=float(W)*float(sen_word[i])

W=1

# 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

# 计算得分

def setiment_score(sententce):

# 1.对文档分词

seg_list = seg_word(sententce)

# 2.将分词结果列表转为dic，然后找出情感词、否定词、程度副词

sen_word, not_word, degree_word = classify_words(list_to_dict(seg_list))

# 3.计算得分

score = socre_sentiment(sen_word, not_word, degree_word, seg_list)

return score

# # 测试

# print(setiment_score("我今天心情很糟糕也不开心"))

workbook = Workbook()

result_sheet = workbook.active

result_sheet.title = "随便"

sheets = xlrd.open_workbook(r'D:\answer.xls').sheets()

#先用第一个sheet试试水

for i in range(1):

sheet = sheets[i]

for j in range(1,sheet.nrows):

a = []

# print(sheet.cell_value(i,3))

create_time = datetime.datetime(*(handle_date(sheet.cell_value(j,3))[:3]))#精确到天

answer = sheet.cell_value(i,4)

a.append(create_time)

a.append(setiment_score(answer))

result_sheet.append(a)

workbook.save("情感数据.xlsx")

原文链接:https://blog.csdn.net/weixin_46660582/article/details/106108514