You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
|
|
|
|
|
import os
|
|
|
|
|
|
from textblob import TextBlob
|
|
|
|
|
|
import pandas as pd
|
|
|
|
|
|
|
|
|
|
|
|
directory = 'E:\\前端\\软件工程\\莎莎和陈梦\\弹幕收集'
|
|
|
|
|
|
|
|
|
|
|
|
#合并所有文件的文本内容
|
|
|
|
|
|
all_text = ""
|
|
|
|
|
|
|
|
|
|
|
|
for filename in os.listdir(directory):
|
|
|
|
|
|
if filename.endswith('.txt'):
|
|
|
|
|
|
filepath = os.path.join(directory, filename)
|
|
|
|
|
|
with open(filepath, 'r', encoding='utf-8') as file:
|
|
|
|
|
|
all_text += file.read() + "\n"
|
|
|
|
|
|
|
|
|
|
|
|
#将合并后的文本保存为一个新的文件
|
|
|
|
|
|
merged_file_path = os.path.join(directory, 'merged_text.txt')
|
|
|
|
|
|
with open(merged_file_path, 'w', encoding='utf-8') as file:
|
|
|
|
|
|
file.write(all_text)
|
|
|
|
|
|
|
|
|
|
|
|
#定义情感分析函数
|
|
|
|
|
|
def analyze_sentiment(text):
|
|
|
|
|
|
blob = TextBlob(text)
|
|
|
|
|
|
return blob.sentiment.polarity, blob.sentiment.subjectivity
|
|
|
|
|
|
|
|
|
|
|
|
#对合并的文本进行情感分析
|
|
|
|
|
|
polarity, subjectivity = analyze_sentiment(all_text)
|
|
|
|
|
|
|
|
|
|
|
|
#打印分析结果
|
|
|
|
|
|
print(f"弹幕的情感极性: {polarity}")#-1 表示非常负面，0 表示中立，1 表示非常正面
|
|
|
|
|
|
print(f"弹幕的情感主观性: {subjectivity}")#0 表示完全客观，1 表示完全主观
|
|
|
|
|
|
|
|
|
|
|
|
#保存分析结果到CSV文件
|
|
|
|
|
|
results = {
|
|
|
|
|
|
'Filename': ['merged_text.txt'],
|
|
|
|
|
|
'Polarity': [polarity],
|
|
|
|
|
|
'Subjectivity': [subjectivity]
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
results_df = pd.DataFrame(results)
|
|
|
|
|
|
results_df.to_csv(os.path.join(directory, 'sentiment_analysis_results.csv'), index=False)
|
