收稿日期: 2015-11-06
修回日期: 2015-12-07
网络出版日期: 2015-12-20
基金资助
本文系ISTIC-THOMSON REUTERS科学计量学联合实验室开放基金项目"基于学科领域多特征项共现的知识图谱分析方法设计与实现——以WoS学科数据为例"和国家自然科学基金管理学部青年项目"基于学科领域科技论文多重共现的情报计量分析方法研究"(项目编号:71403261)研究成果之一。
Research on the Algorithms and Visualization Analysis Tool of the Burst Detection Analysis Method Based on Multiple Relationships in Collections of Journal Papers
Received date: 2015-11-06
Revised date: 2015-12-07
Online published: 2015-12-20
[目的/意义]基于科技论文多特征项共现突发强度的分析方法研究是将各学科领域科技论文文献载体中的多特征项共现信息定量化、重点热点突发的信息内容可视化的知识图谱分析方法。从动态论文等文献的文档流中探测出突发的特征项对识别密集的内容、活跃的特征项以及预测文本内容的发展走势具有重要的意义。[方法/过程]本研究针对科技论文多特征项共现的突发监测问题,对比目前已有的突发监测分析算法,将改进后的基于卡方统计的热点词计算方法进一步应用于本研究所设计的多特征项突发共现分析方法,并自主开发多特征项突发共现可视化分析工具,用于科技论文多特征项突发共现的图谱可视化,以期通过该研究来揭示相关科技文献的变化状况及突发的热点内容。[结果/结论]通过将本方法应用到科研机构年度发表论文的监测当中,可以监测分析科研机构发文作者、关键词、发表期刊及其相互间关系(如作者-关键词等)在各年的突发情况,并能通过该分析方法以及交叉图谱进一步解读突发特征项的含义,并能揭示出比分析单一特征项突发情况更为广泛和深入的知识内容。
庞弘燊 . 基于科技论文多特征项共现突发强度分析方法的算法实现与可视化图谱研究[J]. 图书情报工作, 2015 , 59(24) : 115 -122 . DOI: 10.13266/j.issn.0252-3116.2015.24.017
[Purpose/significance] The burst detection analysis method based on multiple relationships in collections of journal papers is a knowledge discovery method for multiple co-occurrences and hot topics in scientific and technicalpapers. It is significant to detect the research content and predict the research trends in papers' data stream.[Method/process] This paper focused on the burst detection problem of multiple co-occurrences in collections of journal papers. By comparing the algorithms of burst detection, the author selected a suitable algorithm in this research and developed the visualization analysis tool and designs the analysis model for burst detection analysis on multiple co-occurrences. This paper further applied the multiple co-occurrences burst detection method to reveal the research trends and hot topics in a set of institutes' papers.[Result/conclusion] By applying this method to the annual published papers' detection of scientific research institutions, we can analyze the burst detection situation of authors, key words, published journals and their relationships (such as the authors-keywords, etc.). We can also dig out deeper information contents than the general burst detection analysis method.
[1] 洪娜,张智雄,乐小虬. 基于决策树的潜在爆发词探测方法[J]. 情报学报, 2012,31(3):228-241.
[2] 郑乐丹. 基于突发检测的我国数字图书馆研究前沿及其演进分析[J]. 图书馆论坛, 2013, 33(1):47-51.
[3] 袁志坚,王乐,田李,等. 数据流突发检测研究与进展[J]. 计算机工程与应用, 2008, 44(21):1-4.
[4] Zhu Yunyue, Dennis S. Efficient elastic burst detection in data streams[C]//Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington: ACM Press, 2003: 336-345.
[5] Jon K. Bursty and hierarchical structure in streams[C]//Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Edmonton: ACM Press, 2002: 91-101.
[6] Gabriel P,Cheong F. Parameter free bursty events detection in text streams[C]//Proceedings of the 31st International Conference on Very Large Data Bases. Trondheim: VLDB Endowment, 2005: 181-192.
[7] Qin S,Qian Weining, Zhou Aoying. Adaptively detecting aggregation bursts in data streams[J]. Lecture Notes in Computer Science, 2005: 435-446.
[8] Chen Tingting, Wang Yi, Fang Binxing, et al.Detecting lasting and abrupt bursts in data streams using two-layered wavelet tree[C]//International Conference on Internet and Web Applications and Services/Advanced International Conference on Telecommunications.Washington:IEEE Computer Society, 2006: 30-30.
[9] 袁志坚. 数据流突发检测若干关键技术研究[D].北京:国防科学技术大学,2008.
[10] Zhang Xin, Dennis S. Better burst detection[C]//The 22nd International Conference on Data Engineering. Atlanta Washington DC:IEEE Computer Society,2006: 146-149.
[11] Ye Huimin, Chen Wei, Dai Guanzhong.Design and implementation of on-line hot topic discovery model[J]. 武汉大学学报(自然科学英文版), 2006, 11(1):21-26.
[12] Lappas T, Arai B,Platakis M,et al. On burstiness-aware search for document sequences[C]//KDD'09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Paris: ACM, 2009.
[13] He Dan, Parker D S. Topic dynamics: An alternative model of bursts in streams of topics[C]//KDD'10: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington: ACM, 2010.
[14] Swan R, Jensen D. TimeMines: Constructing timelines with statistical models of word usage [EB/OL]. [2015-03-15].http://www.cs.cmu.edu/~dunja/KDDpapers/Swan_TM.pdf.
[15] 薛素芝,鲁然,任圆圆.基于速度增长的微博热点话题发现[J].计算机应用研究,2013, 30(9):2598-2601.
[16] 高辉,王沙沙,傅严,等.Web舆情的长期趋势预测方法[J].电子科技大学学报,2011, 40(3):440-445.
[17] 李勇,安新颖,赵迎光.基于动态时间窗口的突发监测研究[J].医学信息学杂志,2014,35(6): 44-48.
[18] Pang Hongshen.A knowledge discovery method based on analysis of multiple co-occurrence relationships in collections of journal papers[J].Chinese Journal of Library and Information Science,2012,5(4):9-20.
[19] Morris S A. Unified mathematical treatment of complex cascaded bipartite networks: the case of collections of journal papers [D]. Oklahoma: Oklahoma State University, 2005.
[20] 庞弘燊,方曙,范炜,等. 基于多重共现的机构科研状况分析方法研究——以中科院国家科学图书馆为例[J].情报学报,2012,31(11):1140-1152.
[21] Swan R, Allan J. Automatic generation of overview timelines [C]//Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2000:49-56.
[22] Prabowo R, Thelwall M, Alexandrov M. Generating overview timelines for major events in an RSS corpus [J]. Journal of Informetrics, 2007(1):131-144.
[23] Wang Canhui, Zhang Min,Ru Liyun,et al. Automatic online news topic ranking using media focus and user attention based on aging theory [C]//Conference on Information and Knowledge Management. Napa Valley:ACM,2008:1033-1042.
/
| 〈 |
|
〉 |
