This dissertation mainly dicussed the Natural Language Processing (NLP) and Machine Learning (ML) based text classification, in which a new mean-variance based feature reduction was raised and anlyized.

• 本文讨论了基于自然语言处理和机器学习的文本分类任务,提出了文本分类中新的特征降维方法,并结合两种不同的机器学习算法,观察了不同的降维方法和机器学习算法相组合完成文本分类的性能随特征空间维数变化的现象,并尝试探讨了造成这种现象的原因。