使用朴素贝叶斯和Python进行情感分析

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import re
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from wordcloud import WordCloud

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.metrics import (
    accuracy_score, 
    confusion_matrix, 
    classification_report, 
    RocCurveDisplay, 
    PrecisionRecallDisplay
)

# --- 下载NLTK资源 ---
# （只需要运行一次）
# nltk.download('stopwords')
# nltk.download('wordnet')
# nltk.download('omw-1.4') # 用于WordNet

# --- 1. 模拟我们的DataFrame ---
# 在实际项目中，您会在这里使用pd.read_csv()
data = {
    'review': [
        "This movie was absolutely fantastic! The acting was superb.",
        "I loved this film. The story was compelling and beautiful.",
        "A truly great and moving picture. Highly recommend.",
        "What a wonderful movie. I'll watch it again.",
        "The best film I've seen all year.",
        "Completely boring. I fell asleep halfway through.",
        "A terrible plot and awful acting. Do not recommend.",
        "This was a bad movie. Just plain bad.",
        "I hated it. The end was a letdown.",
        "The characters were flat and the story was predictable."
    ],
    'sentiment': [1, 1, 1, 1, 1, 0, 0, 0, 0, 0] # 1 = 正面, 0 = 负面
}
df = pd.DataFrame(data)

1
2
3

sns.countplot(x='sentiment', data=df)
plt.title('类别分布 (0=负面, 1=正面)')
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

positive_text = ' '.join(df[df['sentiment'] == 1]['review'])
negative_text = ' '.join(df[df['sentiment'] == 0]['review'])

# 正面词云
wc_positive = WordCloud(width=800, height=400, background_color='white').generate(positive_text)
plt.figure(figsize=(10, 5))
plt.imshow(wc_positive, interpolation='bilinear')
plt.title('正面评论中最频繁的单词')
plt.axis('off')
plt.show()

1
2
3
4
5
6
7

# 负面词云
wc_negative = WordCloud(width=800, height=400, background_color='black', colormap='Reds').generate(negative_text)
plt.figure(figsize=(10, 5))
plt.imshow(wc_negative, interpolation='bilinear')
plt.title('负面评论中最频繁的单词')
plt.axis('off')
plt.show()

1
2
3
4

df['review_length'] = df['review'].apply(len)
sns.histplot(data=df, x='review_length', hue='sentiment', multiple='stack', bins=20)
plt.title('按情感划分的评论长度分布')
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

stop_words = set(stopwords.words('english'))
lemmatizer = WordNetLemmatizer()

def preprocess_text(text):
    # 1. 转换为小写
    text = text.lower()
    
    # 2. 删除标点符号和数字
    text = re.sub(r'[^a-zA-Z\s]', '', text)
    
    # 3. 分词（拆分成单词）
    words = text.split()
    
    # 4. 删除停用词并进行词形还原
    words = [lemmatizer.lemmatize(word) for word in words if word not in stop_words]
    
    # 5. 重新连接成字符串
    return ' '.join(words)

# 让我们看看"前后"对比
print(f"原始: {df['review'][0]}")
print(f"清理后: {preprocess_text(df['review'][0])}")

# 将此函数应用于整个'review'列
df['cleaned_review'] = df['review'].apply(preprocess_text)

1
2

原始: This movie was absolutely fantastic! The acting was superb.
清理后: movie absolutely fantastic acting superb

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

# 1. 定义我们的特征（X）和目标（y）
X = df['cleaned_review']
y = df['sentiment']

# 2. 分割为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

# 3. 创建Scikit-learn Pipeline
# 这个Pipeline将：
# 1. 应用TfidfVectorizer
# 2. 训练MultinomialNB模型
pipeline = Pipeline([
    ('tfidf', TfidfVectorizer(max_features=5000, ngram_range=(1, 2))),
    ('model', MultinomialNB())
])

# 4. 训练模型
# 我们只需要在pipeline上调用.fit()！
pipeline.fit(X_train, y_train)

# 5. 进行预测
y_pred = pipeline.predict(X_test)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

# 1. 准确率
print(f"准确率: {accuracy_score(y_test, y_pred):.2f}")
print("-" * 40)

# 2. 分类报告
print(classification_report(y_test, y_pred))
print("-" * 40)

# 3. 混淆矩阵
cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',
            xticklabels=['预测负面', '预测正面'],
            yticklabels=['实际负面', '实际正面'])
plt.title('混淆矩阵')
plt.show()

1
2
3
4
5
6

# 绘制ROC曲线
RocCurveDisplay.from_estimator(pipeline, X_test, y_test)
plt.title('朴素贝叶斯分类器的ROC曲线')
plt.plot([0, 1], [0, 1], 'r--', label='随机猜测')
plt.legend()
plt.show()

1
2
3
4

# 绘制精确率-召回率曲线
PrecisionRecallDisplay.from_estimator(pipeline, X_test, y_test)
plt.title('精确率-召回率曲线')
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

def predict_sentiment(text):
    # Pipeline完成所有工作：
    # 1. 预处理文本
    # 2. TF-IDF向量化
    # 3. 预测
    prediction = pipeline.predict([text])[0]
    probability = pipeline.predict_proba([text])[0]

    if prediction == 1:
        return f"正面 (置信度: {probability[1]:.2f})"
    else:
        return f"负面 (置信度: {probability[0]:.2f})"

# 试试看
print(predict_sentiment("This was the best movie I have ever seen!"))
print(predict_sentiment("The acting was stiff and the plot was just awful."))

1
2

正面 (置信度: 0.95)
负面 (置信度: 0.99)