*Python*如何使用自定义情感词库进行中文情感分析

        情感分析（Sentiment Analysis）是指通过自然语言处理技术自动判断文本的情感倾向，如正面、负面或中性。对于中文文本，情感分析通常需要考虑多种因素，包括停用词、程度级别词语、否定词等。本文将详细介绍如何构建一个简单的中文情感分析系统。

1、首先，我们需要准备一些必要的工具和资源：
        jieba库：一个流行的中文分词工具。
        停用词库：用于去除无关紧要的词汇。
        情感词库：包括正面情绪词和负面情绪词。
        程度级别词语：用于调整情感得分。
        否定词：用于处理否定句。

2、加载停用词库
        停用词库通常包含一些常见的词汇，如“的”、“是”等，这些词汇对情感分析没有帮助，需要去除。我们可以通过以下函数加载停用词库：

def load_stopwords(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        stopwords = set(line.strip() for line in f)
    return stopwords

3、加载情感词库
        情感词库通常包含正面情绪词和负面情绪词。我们可以将它们合并成一个字典，其中键为词汇，值为情感得分。以下函数用于加载情感词库：

def load_sentiment_lexicon(positive_file, negative_file):
    positive_lexicon = {}
    with open(positive_file, 'r', encoding='utf-8') as f:
        for line in f:
            word, score = line.strip().split('\t')
            positive_lexicon[word] = int(score)

    negative_lexicon = {}
    with open(negative_file, 'r', encoding='utf-8') as f:
        for line in f:
            word, score = line.strip().split('\t')
            negative_lexicon[word] = int(score)

    lexicon = {**positive_lexicon, **negative_lexicon}
    return lexicon

4、加载程度级别词语
        程度级别词语用于调整情感得分，例如“非常”会增加情感得分，“稍微”会减少情感得分。以下函数用于加载程度级别词语：

def load_degree_words(file_path):
    degree_words = {}
    with open(file_path, 'r', encoding='utf-8') as f:
        for line in f:
            word, multiplier = line.strip().split('\t')
            degree_words[word] = float(multiplier)
    return degree_words

5、加载否定词
        否定词用于处理否定句，例如“不”、“没”等。以下函数用于加载否定词：

def load_negation_words(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        negation_words = set(line.strip() for line in f)
    return negation_words

6、文本预处理
        文本预处理包括分词和去除停用词。我们可以使用jieba进行分词，并去除停用词：

import jieba
import re

def preprocess_text(text, stopwords):
    text = re.sub(r'[^\u4e00-\u9fa5]', '', text)  # 保留中文字符
    words = jieba.lcut(text)
    filtered_words = [word for word in words if word not in stopwords]
    return filtered_words

7、计算情感得分
        最后，我们需要计算文本的情感得分。这涉及到考虑程度级别词语和否定词的影响：

def sentiment_score(text, lexicon, degree_words, negation_words):
    words = preprocess_text(text, stopwords)
    score = 0
    modifier = 1
    negation_flag = False
    
    for word in words:
        if word in degree_words:
            modifier *= degree_words[word]
        elif word in negation_words:
            negation_flag = True
        elif word in lexicon:
            if negation_flag:
                score += lexicon[word] * modifier * -1
                negation_flag = False
            else:
                score += lexicon[word] * modifier
            modifier = 1  # 重置修饰符
    
    return score

8、示例代码

import jieba
import re

# 加载停用词库
def load_stopwords(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        stopwords = set(line.strip() for line in f)
    return stopwords

# 加载情感词库
def load_sentiment_lexicon(positive_file, negative_file):
    positive_lexicon = {}
    with open(positive_file, 'r', encoding='utf-8') as f:
        for line in f:
            word, score = line.strip().split('\t')
            positive_lexicon[word] = int(score)

    negative_lexicon = {}
    with open(negative_file, 'r', encoding='utf-8') as f:
        for line in f:
            word, score = line.strip().split('\t')
            negative_lexicon[word] = int(score)

    lexicon = {**positive_lexicon, **negative_lexicon}
    return lexicon

# 加载程度级别词语
def load_degree_words(file_path):
    degree_words = {}
    with open(file_path, 'r', encoding='utf-8') as f:
        for line in f:
            word, multiplier = line.strip().split('\t')
            degree_words[word] = float(multiplier)
    return degree_words

# 加载否定词
def load_negation_words(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        negation_words = set(line.strip() for line in f)
    return negation_words

# 文本预处理
def preprocess_text(text, stopwords):
    text = re.sub(r'[^\u4e00-\u9fa5]', '', text)  # 保留中文字符
    words = jieba.lcut(text)
    filtered_words = [word for word in words if word not in stopwords]
    return filtered_words

# 计算情感得分
def sentiment_score(text, lexicon, degree_words, negation_words):
    words = preprocess_text(text, stopwords)
    score = 0
    modifier = 1
    negation_flag = False
    
    for word in words:
        if word in degree_words:
            modifier *= degree_words[word]
        elif word in negation_words:
            negation_flag = True
        elif word in lexicon:
            if negation_flag:
                score += lexicon[word] * modifier * -1
                negation_flag = False
            else:
                score += lexicon[word] * modifier
            modifier = 1  # 重置修饰符
    
    return score

# 示例文本
text = "这部电影真是太棒了，但是结局有点糟糕。"

# 文件路径
stopwords_file = 'chineseStopWords.txt'
positive_file = 'positiveWords.txt'
negative_file = 'negativeWords.txt'
degree_file = 'degreeWords.txt'
negation_file = 'negationWords.txt'

# 加载停用词库
stopwords = load_stopwords(stopwords_file)

# 加载情感词库
positive_lexicon = load_sentiment_lexicon(positive_file, negative_file)
negative_lexicon = load_sentiment_lexicon(negative_file, positive_file)
lexicon = {**positive_lexicon, **negative_lexicon}

# 加载程度级别词语
degree_words = load_degree_words(degree_file)

# 加载否定词
negation_words = load_negation_words(negation_file)

# 计算情感得分
score = sentiment_score(text, lexicon, degree_words, negation_words)

print(f"The sentiment score of the text is: {score}")