如何使用Python提取社交媒体数据中的关键词

import tweepy import nltk from nltk.corpus import stopwords from nltk.tokenize import word_tokenize from nltk.stem import WordNetLemmatizer from sklearn.feature_extraction.text import TfidfVectorizer # Twitter API密钥 consumer_key = "YOUR_CONSUMER_KEY" consumer_secret = "YOUR_CONSUMER_SECRET" access_token = "YOUR_ACCESS_TOKEN" access_token_secret = "YOUR_ACCESS_TOKEN_SECRET" # 亿牛云爬虫代理参数设置 proxyHost = "u6205.5.tp.16yun.cn" proxyPort = "5445" proxyUser = "16QMSOML" proxyPass = "280651" # Twitter API身份验证 auth = tweepy.OAuthHandler(consumer_key, consumer_secret) auth.set_access_token(access_token, access_token_secret) # 创建API对象 api = tweepy.API(auth) # 获取社交媒体数据 tweets = api.user_timeline(screen_name="YOUR_SCREEN_NAME", count=10) # 文本修复函数 def text_repair(text): # 进行文本修复的逻辑 # ... return repaired_text # 关键词提取函数 def extract_keywords(text): # 分词 tokens = word_tokenize(text) # 去除停用词 stop_words = set(stopwords.words("english")) filtered_tokens = [token for token in tokens if token.lower() not in stop_words] # 词形还原 lemmatizer = WordNetLemmatizer() lemmatized_tokens = [lemmatizer.lemmatize(token) for token in filtered_tokens] # 构建TF-IDF向量 vectorizer = TfidfVectorizer() tfidf_matrix = vectorizer.fit_transform([" ".join(lemmatized_tokens)]) # 提取关键词 feature_names = vectorizer.get_feature_names() keywords = [feature_names[index] for index in tfidf_matrix.indices] return keywords # 处理每条社交媒体数据 for tweet in tweets: # 获取文本内容 text = tweet.text # 文本修复 repaired_text = text_repair(text) print("修复后的文本：", repaired_text) # 提取关键词 keywords = extract_keywords(repaired_text) print("提取的关键词：", keywords)