摘要
[目的/意义]旨在对今后我国LDA模型研究提供指导。[方法/过程]利用文本挖掘方法及可视化研究工具Citespace,对CNKI数据库中2009—2019年发表的有关LDA模型研究的357篇CSSCI期刊论文,从发表年份、作者、作者机构及关键词等几个方面进行计量分析。[结果/结论]我国LDA模型研究在近10年一直呈现出上升趋势,处于发展阶段,在未来仍有较大的发展空间;国内研究人员及团队的研究较为分散,没有形成较大的合著网络并且在研究主题上过于单一;研究大多集中在算法和模型的开发上,较少涉及在线文本数据方面的应用研究,但随着互联网技术的发展社会网络分析逐渐成为研究热点,过多集中于模型和算法上的状况有所好转;大数据与LDA模型进一步融合将是未来的发展方向。
[Purpose/significance]The paper is to provide guidance for the future LDA model research in China.[Method/process]The paper uses text mining method and visualization tool Citespace to make a biblimetric analysis of 357 CSSCI articles on LDA model published in CNKI database in 2009—2019 from the aspects of publication year author author institution and keywords.[Result/conclusion]The LDA model research in China has been showing an upward trend in recent ten years is in the development stage and there is still a large space for development in the future.The research of domestic researchers and teams is relatively scattered and there is no large-scale coauthored network and the research topic is too single.Most of the research focuses on the development of algorithms and models less on the application of online text data however with the development of Internet technology social network analysis has gradually become a research hotspot and the situation of too much focus on models and algorithms has been improved.Further integration of big data and LDA models will be the future development direction.
作者
陈博
马秀峰
Chen Bo;Ma Xiufeng(School of Communication,Qufu Normal University,Rizhao Shandong 276826;School of Continuing Education,Qufu Normal University,Qufu Shandong 273165)
出处
《情报探索》
2020年第11期128-134,共7页
Information Research
基金
国家社会科学基金一般项目“面向知识流分析的中文文本主题生成模型构建及应用研究”(项目编号:18BTQ069)成果。
