Computer Engineering and Applications ›› 2018, Vol. 54 ›› Issue (1): 186-190.DOI: 10.3778/j.issn.1002-8331.1607-0016

Previous Articles     Next Articles

Classification of SonCi style using machine learning algorithms

ZHAO Jianming1, LI Chunhui2, YAO Nianmin2   

  1. 1.School of Electronic and Information Engineering, Fuqing Branch, Fujian Normal University, Fuqing, Fujian 350300, China
    2.Dalian University of Technology, Dalian, Liaoning 116024, China
  • Online:2018-01-01 Published:2018-01-15



  1. 1.福建师范大学 福清分校 电子与信息工程学院,福建 福清 350300
    2.大连理工大学,辽宁 大连 116024

Abstract: This paper presents a study of the style of SonCi using many machine learning algorithms whose parameters are optimized by the results of experiments. At the same time, the reverse analyses is performed to get which words have the most effects on the decision making. This method can be used in analyzing the writing style of some author.

Key words: machine learning, Natural Language Processing(NLP), SonCi style

摘要: 使用多种机器学习算法对宋词的风格进行了分类研究,通过比较测试结果选择了较优算法和较优的参数配置。同时,对实验的结果进行了回溯分析,定量分析了哪些单字对宋词风格的判定起到更大的作用。这种分析方法可以推广,用来作为作者写作风格的特征进行更进一步的研究分析。

关键词: 机器学习, 自然语言处理, 宋词风格