【摘要】 为了提高情感分类准确率,提出了一种基于改进的TF-IDF与隐朴素贝叶斯的情感分类研究。通过改进的TF-IDF算法提取文本特征词,并根据属性之间的依赖关系添加隐藏的父节点,增强了属性之间的依赖关系,提高了情感分类的准确性。实验结果表明,在平均宏查准率、宏查全率和宏F1值在改进之后的算法分别提高了5%、8%和6%。更多还原

【Abstract】 In order to improve the accuracy of emotion classification,it proposes an improved TF-IDF and hidden naive Bayes based emotion classification research. The improved TF-IDF algorithm is used to extract the text feature words and add hidden parent nodes according to the dependency relationship between attributes,which enhances the dependency relationship between attributes and improves the accuracy of emotion classification.The experimental results show that the improved algorithm increases the average macro precision,macro recall and macro F1 by 5%,8% and 6%,respectively.更多还原