开篇
这边尝试使用三种方法去提取关键词,我希望能通过一些关键词提取出相应的属性,为了修正我们的评论属性,我还会人为去补充相应的特征词典,关于同义词的一些问题暂且放开不考虑。
词频
直接贴出代码
import json
import jieba
import jieba.analyse
from collections import Counter
import string
from zhon.hanzi import punctuation
stopwords = []
stopword = open('data/chinesestopword.txt','rt')
for line in stopword:
stopwords.append(line.strip())
with open('data/oppo_r15.json','r') as f:
data = json.load(f)
review = []
for i in data:
review.append(i['content'])
score = []
for i in data:
score.append(i['score'])
text = ''.join(c for c in review)
words = jieba.cut(text)
words_list = []
for i