[目的/意义]主题排序不仅是信息检索、信息组织研究的基础性问题，也是图书馆学科服务的重要工作，对学科领域研究主题进行有效排序能够帮助科研人员和科研管理部门有效把握学科领域的研究态势，准确定位科研方向，快速做出科研决策。[方法/过程]基于趋势分析提出一种学科研究主题优先级排序算法。首先，在主题提取的基础上，根据发文趋势和引文趋势将每个研究主题按研究等级分为贫乏主题、热点主题、冷点主题、过热主题4个子类。然后，分别对各子类下的主题词进行优先级排序。[结果/结论]在情报学领域的实验表明：本文提出的优先级排序算法能够全方位、细粒度、深层次地展示学科领域研究主题的发展等级，该方法可为从时间维度实现动态情报分析提供新的视角。
[Purpose/significance] Topic sorting is not only the basic problem for information retrieval and information organization, but also an important work of subject service. The effective sorting of subject field research topics can help researchers and decision-making departments to grasp the research situation of the subject field effectively, locate the direction of scientific research accurately and make scientific research decisions quickly.[Method/process] This paper proposes the prioritization algorithm based on the combination of topic extraction and trend analysis. Then it takes the research topics of Library and Information Science as an example to extract the research topics of the sample literature, and each research topic is divided into four sub-topics:poor theme, hot topic, cold point theme, and overheated topic. Next priority ranking is carried out in subclasses.[Result/conclusion] The empirical results show that the priority ranking algorithm can display the development level of research topics in an all-round, fine-grained and deep way. This method provides a new perspective for realizing dynamic intelligence analysis from time dimension.
[1] 张晓林.颠覆数字图书馆的大趋势[J].中国图书馆学报,2011,37(195):4-11.
[2] 刘欣.基于阅读价值的科技文献排序方法研究[D].大连:大连理工大学, 2010.
[3] 王燕鹏.国内基于主题模型的科技文献主题发现及演化研究进展[J].图书情报工作, 2016, 60(3):130-137.
[4] 关鹏,王曰芬.基于LDA主题模型和生命周期理论的科学文献主题挖掘[J].情报学报,2015, 34(3):286-299.
[5] DONOHUE J C. Understanding scientific literature:a bibliographic approach[M].Massachusetts:The MIT Press,1973.
[6] 唐果媛,张薇.基于共词分析法的学科主题演化研究进展与分析[J].图书情报工作,2015,59(5):128-136.
[7] 陈仕吉,王小梅.基于C-value与TF-IDF的文献簇主题识别研究[J].情报学报, 2009,28(6):821-826.
[8] 陈勇跃,田文芳,吴金红.主题领域研究热点跟踪及趋势预测的可视化分析方法研究[J].情报理论与实践,2017,40(6):117-121.
[9] 巴志超,李纲,朱世伟.共现分析中的关键词选择与语义度量方法研究[J].情报学报,2016,35(2):197-207.
[10] SALTON G, WONG A, YANG C S. A vector space model for automatic indexing[J]. Communications of the ACM,1975,18(11):613-620.
[11] DEERWESTER S C. Indexing by latent semantic analysis[J]. Journal of the American Society for Information Science,1990,41(6):391-407.
[12] Probabilistic latent semantic analysis[EB/OL].[2019-02-26]. https://en.wikipedia.org/wiki/Latent_semantic_analysis#Latent_semantic_indexing.
[13] Latent dirichlet allocation[EB/OL].[2019-02-26]. https://max.book118.com/html/2017/0724/123956096.shtm.
[14] Topics over time:a non-Markov continuous-time model of topical trends[EB/OL].[2019-02-26].https://wenku.baidu.com/view/a1b8c42d4b73f242336c5fce.html.
[15] Extracting multilingual topics from unaligned comparable corpora[EB/OL].[2019-02-26]. https://link.springer.com/chapter/10.1007%2F978-3-642-12275-0_39.
[16] 李湘东,巴志超,黄莉.一种基于加权LDA模型和多粒度的文本特征选择方法[J].现代图书情报技术,2015,31(5):42-48.
[17] 王曰芬,傅柱,陈必坤.采用LDA主题模型的国内知识流研究结构探讨:以学科分类主题抽取为视角[J]. 现代图书情报技术,2016,32(4):8-19.
[18] 王连喜,曹树金.学科交叉视角下的网络舆情研究主题比较分析——以国内图书情报学和新闻传播学为例[J].情报学报,2017,36(2):159-169.
[19] 许腾腾,黄恒君.一种改进的Supervised-LDA文本模型及其应用[J].计算机工程,2018,44(1):69-73,78.
[20] 曲靖野,陈震,胡轶楠.共词分析与LDA模型分析在文本主题挖掘中的比较研究[J].情报科学,2018,36(2):18-23.
[21] WANG C H, ZHANG M, RU L Y, et al. Automatic online news topic ranking using media focus and user attention based on aging theory[C]//Proceedings of the 17th ACM conference on information and knowledge management. New York:ACM Press, 2008:1033-1042.
[22] 姜晓伟,王建民,丁贵广.基于主题模型的微博重要话题发现与排序方法[J].计算机研究与发展,2013,50(5):179-185.
[23] 刘培玉,侯秀艳,朱振方.基于热度联合排序的微博热点话题发现[J].计算机科学与探索,2016, 10(4):574-581.
[24] CUI W,LIU S,TAN L,et al. Text flow:towards better understanding of evolving topics in text[J].IEEE transactions on visualization & computer graphics,2011,17(12):2412-2421.
[25] 肖智博.排序主题模型及其应用研究[D].大连:大连海事大学,2014.
[26] XIAO Z,CHE F,MIAO E, et al.Increasing serendipity of recommender system with ranking topic model[J]. Applied mathematics & information sciences, 2014,8(4):2041-2053.
[27] 蒋卓人,高良才,赵星.中英文科技主题排序相关性的比较研究:以计算机领域为例[J]. 情报学报,2017, 36(9):940-953.
[28] ALAM M M,ISMAIL M A.RTRS:a recommender system for academic researchers[J].Scientometrics, 2017,113(1):1-24.
