【终极指南】使用Python可视化分析文本情感倾向

pip install nltk textblob matplotlib

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
nltk.download('stopwords')
nltk.download('punkt')

def preprocess_text(text):
    stop_words = set(stopwords.words('english'))
    word_tokens = word_tokenize(text)
    filtered_text = [word for word in word_tokens if word.lower() not in stop_words and word.isalpha()]
    return ' '.join(filtered_text)

# 示例文本
text = "I am really happy to see you! But I am also a little sad that you have to leave."
processed_text = preprocess_text(text)
print("Processed Text:", processed_text)

from textblob import TextBlob

def analyze_sentiment(text):
    blob = TextBlob(text)
    sentiment = blob.sentiment.polarity
    return sentiment

sentiment_score = analyze_sentiment(processed_text)
print("Sentiment Score:", sentiment_score)

import matplotlib.pyplot as plt

def visualize_sentiment(sentiment_score):
    plt.bar(['Sentiment'], [sentiment_score], color=['blue'])
    plt.ylim(-1, 1)
    plt.ylabel('Sentiment Score')
    plt.title('Sentiment Analysis Result')
    plt.show()

visualize_sentiment(sentiment_score)

from nltk.sentiment.vader import SentimentIntensityAnalyzer

def analyze_sentiment_vader(text):
    analyzer = SentimentIntensityAnalyzer()
    sentiment = analyzer.polarity_scores(text)['compound']
    return sentiment

sentiment_score_vader = analyze_sentiment_vader(processed_text)
print("Sentiment Score (VADER):", sentiment_score_vader)

def visualize_comparison(sentiment_textblob, sentiment_vader):
    plt.bar(['TextBlob', 'VADER'], [sentiment_textblob, sentiment_vader], color=['blue', 'green'])
    plt.ylim(-1, 1)
    plt.ylabel('Sentiment Score')
    plt.title('Sentiment Analysis Comparison')
    plt.show()

visualize_comparison(sentiment_score, sentiment_score_vader)

def classify_sentiment(score):
    if score > 0:
        return "Positive"
    elif score < 0:
        return "Negative"
    else:
        return "Neutral"

sentiment_class_textblob = classify_sentiment(sentiment_score)
sentiment_class_vader = classify_sentiment(sentiment_score_vader)
print("Sentiment Class (TextBlob):", sentiment_class_textblob)
print("Sentiment Class (VADER):", sentiment_class_vader)

def visualize_sentiment_classification(sentiment_classes):
    labels = list(sentiment_classes.keys())
    sizes = [sentiment_classes[label] for label in labels]
    colors = ['gold', 'lightcoral', 'lightskyblue']
    plt.pie(sizes, labels=labels, colors=colors, autopct='%1.1f%%', startangle=140)
    plt.axis('equal')
    plt.title('Sentiment Classification')
    plt.show()

sentiment_classes = {sentiment_class_textblob: 1, sentiment_class_vader: 1}
visualize_sentiment_classification(sentiment_classes)

def visualize_sentiment_multi(sentiment_textblob, sentiment_vader):
    labels = ['TextBlob', 'VADER']
    values = [sentiment_textblob, sentiment_vader]
    colors = ['blue', 'green']
    
    fig, axs = plt.subplots(1, 2, figsize=(10, 5))
    axs[0].bar(labels, values, color=colors)
    axs[0].set_ylim(-1, 1)
    axs[0].set_ylabel('Sentiment Score')
    axs[0].set_title('Sentiment Analysis Result')

    axs[1].pie(values, labels=labels, colors=colors, autopct='%1.1f%%', startangle=140)
    axs[1].set_title('Sentiment Classification')

    plt.tight_layout()
    plt.show()

visualize_sentiment_multi(sentiment_score, sentiment_score_vader)