使用NLP库textblob进行情感分析-红楼梦评论
最近做了一个分析国外读者对红楼梦评价的小项目。这部分是使用textblob库对评论进行情感分析,得到情感值,并且进行分类,生成词云。
生成直方图、条形图的数据分析过程见我的这篇文章
读入的数据是这样的格式。包含两行,一行评论,一行url来源。
生成的结果是这样的result.csv文件
词云图片:
代码如下
from textblob import TextBlob
from wordcloud import WordCloud
import pandas as pd
import numpy as np
import csv
from os import listdir
def getComments(filename): # 获取评论列表、评论中所有的单词,以空格分隔
comments = np.zeros(0)
words = ''
com_file = pd.read_csv(filename)
comments = np.append(comments, com_file['comment'])
for each in comments:
words += each
replace_list = [',', '.', '\'', '\"']
for each in replace_list:
words = words.replace(each, ' ')
return comments, words
def getWordCloud(text_str, picture_name): # 生成词云
wordcloud = WordCloud(background_color="white",width=1980, height=1080, margin=2, random_state=0).generate(text_str)
wordcloud.to_file(picture_name)
def get_p_or_n(comments): # 获取情绪极化评分,并划定阈值确定是积极、消极或中立
with open('result.csv', 'w', encoding='utf-8') as csvfile:
id = 0
writer = csv.writer(csvfile)
writer.writerow(['id', 'result', 'score', 'comment'])
with open('samples.csv', 'w', encoding='utf-8') as samples_file:
writer_samples = csv.writer(samples_file)
writer_samples.writerow(['id', 'result', 'score', 'OurJudge', 'comment'])
for each in comments:
judge = TextBlob(each)
# print(each)
result = ''
score = judge.sentiment.polarity
if score > 0.05:
result = '积极'
elif score < -0.03:
result = '消极'
else:
result = '中立'
id += 1
writer.writerow([id, result, score, each])
if id%5 == 0:
writer_samples.writerow([id, result, score, '', each])
def main():
filename = "comments.csv"
comments, words = getComments(filename)
print(len(comments))
getWordCloud(words, "WordCloud.png")
get_p_or_n(comments)
if __name__ == "__main__":
main()