情感分析之sklearn基于电影评论数据集

import nltk
from nltk.corpus import movie_reviews
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB

nltk.download('movie_reviews')

# 加载数据集
neg_reviews = movie_reviews.fileids('neg')
pos_reviews = movie_reviews.fileids('pos')

# 提取特征
vectorizer = CountVectorizer(stop_words='english')
neg_feats = vectorizer.fit_transform([movie_reviews.raw(fileids=[f]) for f in neg_reviews])
pos_feats = vectorizer.fit_transform([movie_reviews.raw(fileids=[f]) for f in pos_reviews])
X = neg_feats + pos_feats
y = [0] * len(neg_reviews) + [1] * len(pos_reviews)

# 模型训练
model = MultinomialNB()
model.fit(X, y)

# 模型预测
text = "This movie was terrible, the acting was bad and the plot was boring"
feat = vectorizer.transform([text])
sentiment = model.predict(feat)[0]

if sentiment == 0:
    print("Negative review")
else:
    print("Positive review")

在上面的示例中，我们使用了nltk语料库中的电影评论数据集。我们使用CountVectorizer从文本数据中提取特征，并使用MultinomialNB朴素贝叶斯分类器训练模型。然后，我们使用模型对给定文本进行情感分类。