期刊文献+

基于LDA模型的埃博拉病毒英文文献主题分析

Topic analysis of English Ebola virus literature based on LDA model
原文传递
导出
摘要 目的 应用LDA模型及其变形对PUBMED数据库中埃博拉病毒相关文献摘要进行主题识别并分类,了解埃博拉病毒研究文献的领域分布及发展趋势。方法 以PUBMED数据库中含有摘要信息的文献为数据源,使用Python、Endnote 20.1.0等工具,借助LDA模型及其变形对文献进行主题识别与演化分析。结果 应用LDA模型识别出监测预警、感染机制、影响因素、检测诊断、临床治疗、疫苗及致病机制7类主题;得到检测诊断、感染机制及疫苗研发领域主题词随时间发展频率变化。结论 疫情是埃博拉病毒研究的主要驱动力,疫情发生后本领域发文量迅速上升并在疫情消失后回归,预测未来发文量将随着疫情再暴发继续上升;预计未来研究将主要围绕疫情防控以及临床转化开展,而基础研究仍具有巨大发展空间。 s in PUBMED database were selected as data sources,and the topic identification and evolution analysis were carried out by using Python,Endnote 20.1.0 and other tools with the help of LDA model and its deformation.Results LDA model was used to identify 7 themes including surveillance and early warning,infection mechanism,influencing factors,detection and diagnosis,clinical treatment,vaccine and pathogenic mechanism.The frequency changes of detection and diagnosis,infection mechanism and vaccine research and development subject words over time were obtained.Conclusions The epidemic is the main driving force of Ebola virus research.The number of published papers in this field increased rapidly after the outbreak of the epidemic and returned after the epidemic disappeared.It is predicted that the number of published papers will continue to increase with the recurrence of the epidemic in the future.Future research will focus on epidemic prevention and clinical transformation,while basic research still has huge room for development.
作者 杨启帆 朱志华 王磊 YANG Qifan;ZHU Zhihua;WANG Lei(Institute of Health Service and Transfusion Medicine,Academy of Military Medical Sciences,Academy of Military sciences,Beijing 100850,China.)
出处 《预防医学情报杂志》 CAS 2023年第11期1409-1414,共6页 Journal of Preventive Medicine Information
关键词 埃博拉病毒 LA模型 主题识别 演化分析 Ebolavirus The LDA model topics identification evolutionary analysis.
  • 相关文献

参考文献2

二级参考文献42

  • 1王燕.一种改进的K-means聚类算法[J].计算机应用与软件,2004,21(10):122-123. 被引量:9
  • 2Salton G,Wong A, Yang C S. A Vector Space Model for Auto- matic lndexing[J]. Communications of the ACM, 1975,18: 613- 620.
  • 3Blei D, Ng A, Jordan M. Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003,3 : 993.
  • 4石晶,范猛,李万龙.基于LDA模型的主题分析[J].自动化报,2009,36:1586-1593.
  • 5Wei Xing,Croft W Bo LDA-Based Document Models for Ad-hoc Retrieval[C]//SIGIR' 06. Seattle, WA, USA, August 2006.
  • 6Friedman N, Geiger D, Goldszmidt M. Bayesian Network Classi- fiers[J]. Machine Learning, 1997,2 : 131.
  • 7Doueet A, Godsill S, Andrieu C. On sequential Monte Carlo sam- piing methods for Bayesian filtering[J]. Statistics and Compu- ting,2000,3:197.
  • 8Duda R O, Hart P E, Stork D G. Pattern Classification(2ed)[M].李宏东,姚天翔,等译.机械工业出版社,2003:508.
  • 9Lin J. Divergence measures based on Shannon entropy[J]. IEEE Transactions on Infommtion Theory, 1991,37(14) 145.
  • 10Deerwester S, Dumais S T, Furnas G W, et al. Indexing by Latent Semantic Analysis [J]. Journal of the American Society for Information Science, 1990, 41(6): 391-407.

共引文献98

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部