[Purpose/significance] This paper comprehensively uses qualitative and quantitative methods to analyze and compare the innovative features and expression paradigms of Chinese and foreign information science papers in recent years, thus revealing the innovative characteristics of papers in the field of information science, discovering the knowledge relationship within the innovative sentences, and conducting a more fine-grained analysis of the innovation of the papers, which provides conditions for the discovery and utilization of innovations in the research field, and at the same time, enriches the ways of innovation monitoring of research papers and promotes scientific research innovation.[Method/process] Starting from the sentence-level innovative identification, two kinds of information science journals in Chinese and English are selected as samples, and the methods of NLP and machine learning are used to the process of information extraction and classification. This paper extended the extraction of innovative sentences from the existing abstract to the full text, moreover made full use of sentence structure and syntactic features to identify innovative content in the field, and explored the characteristics of Chinese and foreign information science papers in terms of innovation objects, themes, categories, etc., meanwhile made a comparative analysis. Finally, through qualitative analysis of the automatic classification of document collections, the paper summarized the expression paradigms of the innovation of Chinese and foreign papers.[Result/conclusion] From the expression of innovation points, the distribution of innovative sentences in Chinese and foreign information science papers is basically the same. The expression of innovation in foreign papers is richer. In terms of the characteristics of innovation, the innovation topics of foreign information science journals are concentrated, while the Chinese ones are diversified and scattered. The innovation of specific methods is a hot spot in the field of information science in recent years. The innovation characteristics of both Chinese and foreign information science journal papers reflect the results of applied research and empirical research are richer, while the trend of theoretical innovation is slow.
[1] TAN R. On the declaration of novelty in scientific journal articles[EB/OL].[2019-10-30]. https://www.philstar.com/business/science-and-environment/2014/04/24/1315251/declaration-novelty-scientific-journal-articles.
[2] 徐书荣.科技期刊编辑对提升论文创新性的作用[J].中国科技期刊研究, 2014,25(6):761-764.
[3] GABRILOVICH E, DUMAIS S T, HORVITZ E, et al. Newsjunkie:providing personalized newsfeeds via analysis of information novelty[C]//Proceedings of the 13th international conference on World Wide Web. New York:ACM, 2004:482-490.
[4] OBEID N, RAO R B K N. On integrating event definition and event detection[J]. Knowledge and information systems, 2010, 22(2):129-158.
[5] TSAI F S, CHAN K L. Redundancy and novelty mining in the business blogosphere[J]. The learning organization, 2010, 17(6):490-499.
[6] BREJA M. A novel approach for novelty detection of web documents[J]. International journal of computer science and information technologies, 2015, 6(5):4257-4262.
[7] LI X, CROFT W B. Novelty detection based on sentence level patterns[C]//Proceedings of the 14th ACM international conference on Information and knowledge management.New York:ACM, 2005:744-751.
[8] 张帆,乐小虬.领域科技文献创新点句中主题属性实例识别方法研究[J].数据分析与知识发现, 2015, 31(5):15-23.
[9] 温浩.科技文摘创新点语义识别与分类方法研究[J].情报学报, 2019, 38(03):27-34.
[10] 刘齐进,程齐凯,陆伟.学术文献创新修饰词描述对象分析[C]//南京:第九届全国情报学博士生学术论坛. 2019.
[11] Merriam-Webster, Incorporated.Merriam-Webster Online Dictionary.[EB/OL].[2019-10-30]. http://www.merriam-webster.com.
[12] NG K W, TSAI F S, CHEN L C L, et al. Novelty detection for text documents using named entity recognition[C]//International Conference on Information. Piscataway:IEEE, 2008.
[13] ALLAN J, WADE C, BOLIVAR A. Retrieval and novelty detection at the sentence level[C]//Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval. New York:ACM, 2003:314-321.
[14] UZZI B, MUKHERJEE S, STRINGER M J, et al. Atypical combinations and scientific impact[J]. Science, 2013, 342(6157):468-472.
[15] ARTHUR W B. The nature of technology:what it is and how it evolves[M]. New York:Simon and schuster, 2009.
[16] 周露阳.论审评学术论文创新因素的指标体系[J].编辑学报,2006(01):68-70.
[17] 贺婉莹.基于机器学习的论文学术创新力评价研究[D].南京:南京大学,2019.
[18] 刘丽萍,刘春丽.开放同行评议利弊分析与建议[J].中国科技期刊研究,2017,28(05):389-395.
[19] 王晓慧,王康.基于期刊论文的学者学术影响力评价及评价指标关系研究——以竞争情报研究领域为例[J].情报科学,2018,36(02):63-66,87.
[20] LEE Y, WALSH J, WANG J, et al. Creativity in scientific teams:unpacking novelty and impact[J]. Research policy, 2015, 44(3):684-697.
[21] WU L, WANG D, EVANS J A, et al. Large teams develop and small teams disrupt science and technology[J]. Nature, 2019, 566(7744):378-382.
[22] 宋歌.科研成果创新力指标S指数的设计与实证[J].图书情报工作,2016,60(05):77-86,124.
[23] 叶继元.学术期刊的质量与创新评价[J].浙江大学学报(人文社会科学版),2013,43(02):108-117.
[24] 李如森,彭彩红,赵福荣.科技论文创新性判断方法[J].鞍山钢铁学院学报,2001(03):234-236.
[25] 杨建林,钱玲飞.基于关键词对逆文档频率的主题新颖度度量方法[J].情报理论与实践,2013,36(03):99-102.
[26] 梁帅,高继平.基于F5000论文评审意见的优秀论文特征识别[J].科学学研究,2017,35(03):331-337.
[27] 钱玲飞,张吉玉,汪荣,等.基于领域知识的学术创新力测度本体构建研究[J].现代情报,2019,39(05):30-37.
[28] 崔京艳,邓媛,李春梅,等.中医学科技论文创新性和科学性的识别与评价[J].中国医药导报,2018,15(05):172-176.
[29] 曹小春.学术期刊审稿专家的职责[J].编辑之友,2006(06):62-63.
[30] 索传军.知识转移视角下的学术论文老化与创新研究[J].图书情报工作,2014,58(05):5-12.
[31] HEINZE T, SHAPIRA P, SENKER J, et al. Identifying creative research accomplishments:Methodology and results for nanotechnology and human genetics[J]. Scientometrics, 2007, 70(1):125-152.
[32] 朱大明.参考文献的主要作用与学术论文的创新性评审[J].编辑学报,2004(02):91-92.
[33] CANNON D C, YANG J J, MATHIAS S L, et al. TIN-X:target importance and novelty explorer[J]. Bioinformatics, 2017, 33(16):2601-2603.
[34] 沈阳.一种基于关键词的创新度评价方法[J].情报理论与实践,2007(01):125-127.
[35] OHSAWA Y, BENSON N E, YACHIDA M. KeyGraph:automatic indexing by co -occurrence graph based on building construction metaphor[C]//Proceedings of IEEE international forum on research and technology advances in digital libraries.Washington:IEEE,1998:12-18.
[36] 杨京,王芳,白如江.一种基于研究主题对比的单篇学术论文创新力评价方法[J].图书情报工作,2018,62(17):75-83.
[37] THORLEUCHTER D. Finding new technological ideas and inventions with text mining and technique philosophy[M]//Data analysis, machine learning and applications. Springer, Berlin, Heidelberg, 2008:413-420.
[38] TANG W, TSAI F S, CHEN L. Blended metrics for novel sentence mining[J]. Expert systems with applications, 2010, 37(7):5172-5177.
[39] FU X, CH'NG E, AICKELIN U. An improved system for sentence-level novelty detection in textual streams[C]//3rd International Conference on Smart Sustainable City and Big Data (ICSSC). London:IET, 2015.
[40] AMORIM M, BORTOLOTI F D, CIARELLI P M, et al. Novelty detection in social media by fusing text and image into a single structure[J]. IEEE access, 2019, 7:132786-132802.
[41] 虞沪生,张瑞清,阎为民.科技论文创新性的审读[J].编辑学报,2006(05):333-334.
[42] DAHL T. The linguistic representation of rhetorical function:a study of how economists present their knowledge claims[J]. Written communication, 2009, 26(4):370-391.
[43] PARKINSON J. The discussion section as argument:the language used to prove knowledge claims[J]. English for specific purposes, 2011, 30(3):164-175.
[44] 张帆,乐小虬.面向领域科技文献的句子级创新点抽取研究[J].现代图书情报技术,2014(09):15-21.
[45] 李璐.信息资源产业与文化产业融合的实证分析——基于中国上市公司1997年-2012年数据[J].情报科学,2016,34(03):122-126.
[46] 李爱明.基于本体和用户查询意图的查询扩展方法研究[J].情报科学,2015,33(05):68-71.
[47] 魏德志,陈福集,林丽娜.一种基于时间序列的热点话题发现模型和算法[J].情报科学,2017,35(10):142-146.
[48] CAO X, CHEN Y, LIU K J, et al. A data analytic approach to quantifying scientific impact[J]. Journal of informetrics, 2016, 10(2):471-484.
[49] ROUSSEAU R, ZHAO S X. A general conceptual framework for characterizing the ego in a network[J]. Journal of informetrics, 2015, 9(1):145-149.
[50] KLAVANS R, BOYACK K W. Mapping altruism[J]. Journal of informetrics, 2014, 8(2):431-447.
[51] 郑捷.NLP汉语自然语言处理[M]. 北京:电子工业出版社,2017:283-287.
[52] 李瑛,周立.科技期刊论文创新点合理呈现的价值及理想模式[J].中国科技期刊研究,2018,29(10):993-999.
[53] GB 7713-1987. 科学技术报告、学位论文和学术论文的编写格式[S].北京:中国标准出版社,1987.
[54] 魏瑞斌.基于内容分析的国内图书情报学研究方法创新研究——以共词分析方法为例[J].图书情报工作,2016,60(24):107-114.
[55] 《数据分析与知识发现》编辑部.《数据分析与知识发现》介绍[EB/OL].[2019-11-02].http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/column/column291.shtml.
[56] 刘智锋,李信,程齐凯,等.学术文本关键词语义功能数据集构建与分析——以Journal of Informetrics为例[J].图书馆论坛,2019,39(07):64-74.
[56] 纪蓉琴.中英思维模式差异对英汉学术论文写作的影响[J].华东交通大学学报,2006(06):134-137.
[57] 魏瑞斌,刘宇.基于标题文本分析的博士论文选题创新性研究——以国内情报学博士论文为例[J].情报杂志,2017,36(07):122-127.
