数智赋能视域下侗族大歌主题挖掘及演化分析研究  

Research on the theme mining and evolution analysis of the Dong Chorus from the perspective of data intelligence empowerment

作　　者：杨秀璋 武帅 项美玉 廖文婧[1] 任天舒 刘建义 Yang Xiuzhang;Wu Shuai;Xiang Meiyu;Liao Wenjing;Ren Tianshu;Liu Jianyi(School of Information,Guizhou University of Finance and Economics,Guiyang,Guizhou 550025,China;School of Information Management of Nanjing Agricultural University;Guiyang School of Big Data and Finance,School of Big Data Application and Economics,Guizhou University of Finance and Economics)

机构地区：[1]贵州财经大学信息学院,贵州贵阳550025 [2]南京农业大学信息管理学院 [3]贵州财经大学大数据应用与经济学院(贵阳大数据金融学院)

出　　处：《计算机时代》2023年第5期118-122,126,共6页Computer Era

基　　金：贵州省科技计划项目(黔科合基础[2020]1Y279,黔科合基础[2019]1041);贵州省教育厅青年科技人才成长项目(No.黔教合KY字[2016]175,No.黔教合KY字[2021]135);贵州财经大学2021年度校级项目(No.2021KYQN03)。

摘　　要：针对新范式对传统人文社科造成学科边界模糊的问题,提出一种基于LDA模型和关系图谱的领域主题演化算法。首先运用综合指数确认领域核心研究人员;再利用LDA模型和层次聚类确认领域划分的主题数,构建关系图谱,探究主题词关联性;最后创新性的提出演化各主题间的关联性。实验将侗族大歌领域分为三个主题,并演化出他们之间的联系。该研究可为数智赋能语音音频的深入研究提供基础。Aiming at the problem that the new paradigm has blurred the boundaries of traditional humanities and social sciences,a domain theme evolution algorithm based on the LDA model and relationship map is proposed.Firstly,the composite index is used to identify core researchers in the domain.Secondly,the LDA model and hierarchical clustering are used to confirm the number of themes divided by the domain,and a relationship map is constructed to explore the relevance of theme words.Finally,the innovative proposal is made to evolve the relevance among the themes.In the experiments,the domain of the Dong Chorus is divided into three themes and the relationship between them is evolved.The research can provide a basis for the in-depth study of data intelligence empowering voice audio.

关 键 词：侗族大歌 数智赋能 领域主题挖掘 关系图谱 主题演化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]