基于NLP和统计方法的唐代不同时期诗歌风格特征分析

大理大学学报 ›› 2023, Vol. 8 ›› Issue (12): 88-96.

基于NLP和统计方法的唐代不同时期诗歌风格特征分析

大理大学数学与计算机学院，云南大理　671003

收稿日期:2023-03-15 出版日期:2023-12-15 发布日期:2024-01-07
通讯作者: 张朝元，教授，博士，Ｅ-mail：zcy_km@163.com。
作者简介:马明，2020级数学与应用数学专业本科生。
基金资助:
国家自然科学基金项目（41664005；41464004）；大理大学科研发展基金项目（FZ2023YB035；FZ2023YB039）；大理大学教育教学改革研究项目（2022JGY08-99；2022JGY08-13）

Analysis of Stylistic Features of Tang Dynasty Poetry in Different Periods Based on NLP and Statistical Methods

College of Mathematics and Computer，Dali University，Dali，Yunnan 671003，China

Received:2023-03-15 Online:2023-12-15 Published:2024-01-07

摘要/Abstract

摘要： 唐诗是我国的文化瑰宝，其数量大，风格和主题多样。为了对不同时期唐诗的特征进行讨论，基于自然语言处理（natural language processing， NLP），利用K-means++聚类分析、重复测量方差分析和配对样本t检验等统计方法对初唐、盛唐、中唐、晚唐4个时期诗歌的风格特征和差异进行分析。结果发现，初唐和盛唐两个时期的诗歌风格具有较为明显的差异，中唐和晚唐差异较小。

关键词:

, NLP；K-means++聚类分析；方差分析；唐代诗歌；特征分析

Abstract:

Tang dynasty poetry is a cultural treasure of China， with a large number of works， diverse styles and themes. In order to discuss the characteristics of Tang dynasty poetry in different periods， this paper used natural language processing （NLP） and statistical methods such as K-means++ clustering analysis， repeated measures ANOVA， and paired sample t-test to analyze the stylistic characteristics and differences of poetry in the Early Tang， Golden Age of Tang， Middle Tang， and Late Tang periods.The results showed that there were significant differences in the poetic styles between the Early Tang and Golden Age of Tang periods， while the differences between the Middle Tang and Late Tang periods were relatively small.

Key words:

NLP, K-means++ clustering analysis, ANOVA, Tang dynasty poetry, feature analysis

中图分类号:

I222.7

马　明, 沈凡起, 张朝元.

基于NLP和统计方法的唐代不同时期诗歌风格特征分析 [J]. 大理大学学报, 2023, 8(12): 88-96.

Ma Ming, Shen Fanqi, Zhang Chaoyuan.

Analysis of Stylistic Features of Tang Dynasty Poetry in Different Periods Based on NLP and Statistical Methods [J]. Journal of Dali University, 2023, 8(12): 88-96.