检测推文是否相似的函数

import re
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics.pairwise import cosine_similarity

def tweetSimilarityDetection(tweet1, tweet2):
    # 预处理推文
    tweet1 = preprocessTweet(tweet1)
    tweet2 = preprocessTweet(tweet2)
    
    # 转换为词向量表示
    vectorizer = CountVectorizer()
    X = vectorizer.fit_transform([tweet1, tweet2])
    
    # 计算相似度得分
    similarityScore = cosine_similarity(X)[0][1]
    
    return similarityScore

def preprocessTweet(tweet):
    # 去除特殊字符、标点符号、URL链接等
    tweet = re.sub(r"[^a-zA-Z0-9]", " ", tweet)
    tweet = re.sub(r"http\S+|www\S+|https\S+", "", tweet)
    tweet = tweet.lower()
    
    return tweet

# 示例用法
tweet1 = "Check out this amazing article on cloud computing!"
tweet2 = "New blog post about the benefits of cloud computing."
similarityScore = tweetSimilarityDetection(tweet1, tweet2)
print("Similarity score:", similarityScore)