Python使用大连理工情感本体提取文本的情感倾向

import pandas as pd
# 导入词典
df = pd.read_excel('Sentiment_dictionary\大连理工情感词汇本体\情感词汇本体.xlsx')
# 我们暂时只使用 ['词语','词性种类','词义数','词义序号','情感分类','强度','极性']
df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]
df.head()

# 按照7大情绪划分
Happy = []
Good = []
Surprise = []
Anger = []
Sad = []
Fear = []
Disgust = []
for idx, row in df.iterrows():
    if row['情感分类'] in ['PA', 'PE']:
        Happy.append(row['词语'])
    if row['情感分类'] in ['PD', 'PH', 'PG', 'PB', 'PK']:
        Good.append(row['词语']) 
    if row['情感分类'] in ['PC']:
        Surprise.append(row['词语'])     
    if row['情感分类'] in ['NA']:
        Anger.append(row['词语'])    
    if row['情感分类'] in ['NB', 'NJ', 'NH', 'PF']:
        Sad.append(row['词语'])
    if row['情感分类'] in ['NI', 'NC', 'NG']:
        Fear.append(row['词语'])
    if row['情感分类'] in ['NE', 'ND', 'NN', 'NK', 'NL']:
        Disgust.append(row['词语'])
Positive = Happy + Good +Surprise
Negative = Anger + Sad + Fear + Disgust
print('情绪词语列表整理完成')

# 计情绪计算函数
# 这里只是朴素的使用情绪词计数统计文本的情绪值
import jieba
import time
def emotion_caculate(text):
    positive = 0
    negative = 0
    anger = 0
    disgust = 0
    fear = 0
    sad = 0
    surprise = 0
    good = 0
    happy = 0
    wordlist = jieba.lcut(text)
    wordset = set(wordlist)
    wordfreq = []
    for word in wordset:
        freq = wordlist.count(word)
        if word in Positive:
            positive+=freq
        if word in Negative:
            negative+=freq
        if word in Anger:
            anger+=freq
        if word in Disgust:
            disgust+=freq
        if word in Fear:
            fear+=freq
        if word in Sad:
            sad+=freq
        if word in Surprise:
            surprise+=freq
        if word in Good:
            good+=freq
        if word in Happy:
            happy+=freq
    emotion_info = {
        'length':len(wordlist),
        'positive': positive,
        'negative': negative,
        'anger': anger,
        'disgust': disgust,
        'fear':fear,
        'good':good,
        'sadness':sad,
        'surprise':surprise,
        'happy':happy,
    }
    indexs = ['length', 'positive', 'negative', 'anger', 'disgust','fear','sadness','surprise', 'good', 'happy']
    return pd.Series(emotion_info, index=indexs)
emotion_caculate(text='这个国家再对这些制造假冒伪劣食品药品的人手软的话，那后果真的会相当糟糕。坐牢？从快判个死刑！')

输出结果：