Joint Modeling of Citation Networks and User Preferences for Academic Tagging Recommender System

In the tag recommendation task on academic platforms,existing methods disregard users’customized preferences in favor of extracting tags based just on the content of the articles.Besides,it uses co-occurrence techniques and tries to combine nodes’textual content for modelling.They still do not,however,directly simulate many interactions in network learning.In order to address these issues,we present a novel system that more thoroughly integrates user preferences and citation networks into article labelling recommendations.Specifically,we first employ path similarity to quantify the degree of similarity between user labelling preferences and articles in the citation network.Then,the Commuting Matrix for massive node pair paths is used to improve computational performance.Finally,the two commonalities mentioned above are combined with the interaction paper labels based on the additivity of Poisson distribution.In addition,we also consider solving the model’s parameters by applying variational inference.Experimental results demonstrate that our suggested framework agrees and significantly outperforms the state-of-the-art baseline on two real datasets by efficiently merging the three relational data.Based on the Area Under Curve(AUC)and Mean Average Precision(MAP)analysis,the performance of the suggested task is evaluated,and it is demonstrated to have a greater solving efficiency than current techniques.

Tracking direct and indirect impact on technology and policy of transformative research via ego citation network

Purpose:The disseminating of academic knowledge to nonacademic audiences partly relies on the transition of subsequent citing papers.This study aims to investigate direct and indirect impact on technology and policy originating from transformative research based on ego citation network.Design/methodology/approach:Key Nobel Prize-winning publications(NPs)in fields of gene engineering and astrophysics are regarded as a proxy for transformative research.In this contribution,we introduce a network-structural indicator of citing patents to measure technological impact of a target article and use policy citations as a preliminary tool for policy impact.Findings:The results show that the impact on technology and policy of NPs are higher than that of their subsequent citation generations in gene engineering but not in astrophysics.Research limitations:The selection of Nobel Prizes is not balanced and the database used in this study,Dimensions,suffers from incompleteness and inaccuracy of citation links.Practical implications:Our findings provide useful clues to better understand the characteristics of transformative research in technological and policy impact.Originality/value:This study proposes a new framework to explore the direct and indirect impact on technology and policy originating from transformative research.

Recommending Authors and Papers Based on ACTTM Community and Bilayer Citation Network

Citation network is often used for academic recommendation. However, it is difficult to achieve high recommendation accuracy and low time complexity because it is often very large and sparse and different citations have different purposes. What's more, some citations include unreasonable information, such as in case of intentional self-citation. To improve the accuracy of citation network-based academic recommendation and reduce the time complexity, we propose an academic recommendation method for recommending authors and papers. In which, an author-paper bilayer citation network is built, then an enhanced topic model, Author Community Topic Time Model(ACTTM) is proposed to detect high quality author communities in the author layer, and a set of attributes are proposed to comprehensively depict the author/paper nodes in the bilayer citation network. Experimental results prove that the proposed ACTTM can detect high quality author communities and facilitate low time complexity, and the proposed academic recommendation method can effectively improve the recommendation accuracy.

Motif-based Classification in Journal Citation Networks

Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This paper presents the idea of using motifs, subgraphs with higher occurrence in real network than in random ones, to discover two different citation patterns in journal communities. And a further investigation is addressed on both motif granularity and node centrality to figure out some reasons on the differences between two kinds of communities in journal citation network.

Scientific Communities Found Based on the Path Structure of Citation Network

Based on the structure of citation network, the citation paths among papers, and the association strength such as coupling, co-citation and etc. between two papers are defined in this article. We give formulas to quantify the association strength in order to establish citation network model based on the citation path structure. Then, the OPTICS algorithm is brought into the scientific communities found model since it can solve the parameter’s setting problem. This method combines various kinds of path structures together and thus it contains more complete citation network information. Experiments and analysis reveal the reliability and validity of this method.

Research on overlapping structures and evolution properties of co-citation network

Purpose: This paper intends to explore methodologies and indicators for the analysis of overlapping structures and evolution properties in a co-citation network, and provide reference for overlapping structure analysis of other scientific networks.Design/methodology/approach: The Q-value variance is defined to achieve overlapping structures of different levels in the scientific networks. At the same time, analyses for time correlation variance and subject correlation variance are used to present the formation of overlapping structures in scientific networks. As a test, a co-citation network of highly cited papers on Molecular Biology & Genetics from Essential Science Indicator(ESI) is taken as an example for an empirical analysis.Findings: Our research showed that the Q-value variance is effective for achieving the desired overlapping structures. Meanwhile, the time correlation variance and subject correlation variance are equally useful for uncovering the evolution progress of scientific research, and the properties of overlapping structures in the research of co-citation network as well.Research limitations: In this paper, the theoretical analysis and verification of time and subject correlation variances are still at its initial stage. Further studies in this regard need to take actual evolution of research areas into consideration.Practical implications: Evolution properties of overlapping structures pave the way for overlapping and evolution analysis of disciplines or areas, this study is of practical value for the planning of scientific and technical innovation.Originality/value: This paper proposes an analytical method of time correlation variance and subject correlation variance based on the evolution properties of overlapping structures, which would provide the foundation for the evolution analysis of disciplines and interdisciplinary research.

Structures and dynamics of scientific knowledge networks:An empirical analysis based on a co-word network

Co-word networks are constructed with author-provided keywords in academic publications and their relations of co-occurrence.As special form of scientific knowledge networks,they represent the cognitive structure of scientific literature.This paper analyzes the complex structure of a co-word network based on 8,190 author-provided keywords extracted from 3,651 papers in five Chinese core journals in the field of management science.Small-world and scale-free phenomena are found in this network.A large-scale co-word network graph,which consists of one major giant component and many small isolated components,has been generated with the GUESS software.The dynamic growth of keywords and keyword co-occurrence relationships are described with four new informetrics measures.The results indicate that existing concepts always serve as the intellectual base of new ideas as represented by keywords.

An Informetric analysis of web citation in Chinese journals of Library and Information Science in recent years

This paper selects 998 articles as its data sources from four Chinese core journals in the field of Library and Information Science from 2003 to 2007.Some pertinent aspects of reference citations particularly from web resources are selected for a focused analysis and discussion.This includes primarily such items as the number of web citations,web citations per each article,the distribution of domain names of web citations and also certain aspects about the institutional and/or geographical affiliations of the author.The evolving situation of utilizing online networked academic information resources in China is the central thematic discussion of this study.The writing of this paper is augmented by the explicatory presentation of 3 graphic figures,6 tables and 18 references.

Evolution of the Socio-cognitive Structure of Knowledge Management(1986–2015): An Author Co-citation Analysis

Purpose: The evolution of the socio-cognitive structure of the field of knowledge management(KM) during the period 1986–2015 is described. Design/methodology/approach: Records retrieved from Web of Science were submitted to author co-citation analysis(ACA) following a longitudinal perspective as of the following time slices: 1986–1996, 1997–2006, and 2007–2015. The top 10% of most cited first authors by sub-periods were mapped in bibliometric networks in order to interpret the communities formed and their relationships.Findings: KM is a homogeneous field as indicated by networks results. Nine classical authors are identified since they are highly co-cited in each sub-period, highlighting Ikujiro Nonaka as the most influential authors in the field. The most significant communities in KM are devoted to strategic management, KM foundations, organisational learning and behaviour, and organisational theories. Major trends in the evolution of the intellectual structure of KM evidence a technological influence in 1986–1996, a strategic influence in 1997–2006, and finally a sociological influence in 2007–2015.Research limitations: Describing a field from a single database can offer biases in terms of output coverage. Likewise, the conference proceedings and books were not used and the analysis was only based on first authors. However, the results obtained can be very useful to understand the evolution of KM research.Practical implications: These results might be useful for managers and academicians to understand the evolution of KM field and to(re)define research activities and organisational projects.Originality/value: The novelty of this paper lies in considering ACA as a bibliometric technique to study KM research. In addition, our investigation has a wider time coverage than earlier articles.

Citation and bibliographic coupling between authors in the field of social network analysis

Purpose:We analyzed the structure of a community of authors working in the field of social network analysis(SNA)based on citation indicators:direct citation and bibliographic coupling metrics.We observed patterns at the micro,meso,and macro levels of analysis.Design/methodology/approach:We used bibliometric network analysis,including the“temporal quantities”approach proposed to study temporal networks.Using a two-mode network linking publications with authors and a one-mode network of citations between the works,we constructed and analyzed the networks of citation and bibliographic coupling among authors.We used an iterated saturation data collection approach.Findings:At the macro-level,we observed the global structural features of citations between authors,showing that 80%of authors have not more than 15 citations from other works.At the meso-level,we extracted the groups of authors citing each other and similar to each other according to their citation patterns.We have seen a division of authors in SNA into groups of social scientists and physicists,as well as into other groups of authors from different disciplines.We found some examples of brokerage between different groups that maintained the common identity of the field.At the micro-level,we extracted authors with extremely high values of received citations,who can be considered as the most prominent authors in the field.We examined the temporal properties of the most popular authors.Research limitations:The main challenge in this approach is the resolution of the author’s name(synonyms and homonyms).We faced the author disambiguation,or“multiple personalities”(Harzing,2015)problem.To remain consistent and comparable with our previously published articles,we used the same SNA data collected up to 2018.The analysis and conclusions on the activity,productivity,and visibility of the authors are relative only to the field of SNA.Practical implications:The proposed approach can be utilized for similar objectives and identifying key structures and characteristics in other disciplines.This may potentially inspire the application of network approaches in other research areas,creating more authors collaborating in the field of SNA.Originality/value:We identified and applied an innovative approach and methods to study the structure of scientific communities,which allowed us to get the findings going beyond those obtained with other methods.We used a new approach to temporal network analysis,which is an important addition to the analysis as it provides detailed information on different measures for the authors and pairs of authors over time.

“一带一路”共建国家间的技术扩散——基于技术内容与网络结构的分析

技术扩散是强化国际经济与创新联系的有效途径,是构建高质量开放创新体系的重要方式。国际技术扩散作为两个主体间的技术扩散活动具有方向性,不同国家的创新政策和技术发展战略侧重点不同,在技术扩散能力和技术吸收能力上均有差异。因而国家间需要构建高效、稳定的技术扩散网络,充分发挥自身的技术优势、补齐技术短板,进一步加大技术流动和增强创新能力。本研究基于技术扩散理论,运用专利引证数据构建“一带一路”共建国家间技术扩散网络,分时段纵向分析共建国家技术扩散网络的演化,分技术领域横向分析共建国家间技术扩散的特征,探索中国与共建国家间技术扩散的内容和路径。研究认为:中国在共建国家技术扩散网络中的核心地位逐步确立,且在“一带一路”倡议提出后中国的核心位置更加明显、技术扩散范围更加广泛;但整体技术扩散网络密度低,除中国外的其他国家间技术扩散关系构建较少;不同技术领域的技术扩散网络形态各有不同,其中化学技术领域的技术扩散最活跃、网络复杂度最高;俄罗斯在化学、机械工程、仪器、其他技术领域具有一定技术优势,并且对中国的技术扩散强度很大,而中国在电气工程技术领域更有技术扩散优势。

科学数据引用网络建模及演化特征分析--以基因表达数据集为例

[目的/意义]将社会网络分析方法应用于科学数据引用特征及规律研究,可以直观呈现出数据引用的复杂网络结构,挖掘数据引用更深层次的价值。[方法/过程]通过辨析科学数据引用特征,构建GEO数据共被引网络模型,并对网络的整体演化、核心个体、社区结构等进行分析。[结果/结论]研究结果表明,GEO数据共被引网络的度和度分布空间差异明显,平均路径长度较短且聚集系数较大,网络中核心个体优势明显,社区结构稳定且特征突出,社区间联系逐渐增强。

基于知识流动的技术守门人识别——以区块链技术领域为例

[目的/意义]技术守门人是影响新技术信息传播的关键角色,有效识别守门人有利于更好地扶持领域内技术创新主体。[方法/过程]文章以技术守门人的定义为基础,并结合科学—技术互动关联理论,选取区块链技术领域为研究对象,构建学者合作网络与引用网络,在原有技术守门人识别方法的基础上,筛选对知识流动有促进作用的守门人。[结果/结论]实验结果显示,运用该方法筛选出的守门人在知识流动过程中具有控制和促进作用,与传统守门人相比,该方法识别出的守门人对领域发展的贡献与促进作用更为突出,对专业领域的发展更具影响力。

基于知识元引用网络的细分领域演化特征研究

[目的/意义]理解科学知识发展演化过程有助于促进科学研究,从微观视角追踪知识在细分领域中的结构与演化特征对知识评估和知识服务具有重要意义。[方法/过程]以医学信息学中知识元为例,利用语义类型界定每种疾病的治疗相关细分领域,构建125种疾病不同时刻的知识元引用网络,采用Leiden算法识别知识群落,从群落知识演化、群落知识竞争状态等维度揭示疾病个体的演化特征;提出丰富度、均衡性与差异度三种测度指标,揭示疾病个体与整体的多样性特征。[结果/结论]研究表明,知识元引用网络中的群落能够反映出疾病知识结构与演进状态。整体层次的疾病知识多样性特征包括:疾病知识群落数量不断增加,群落间规模与组成差异不断扩大;不同疾病表现出常规型、早期争议型、泛指型演化模式;研究较早的疾病普遍均衡性较低、差异度较高。

基于参考文献的论文跨学科性、跨时域性及其影响力研究

本文在跨学科性概念的基础上,提出了跨时域性的测度框架,并将其量化为时域丰富性、时域非均衡性、时域差异性和时域深度4个维度。本文对微软学术数据库中1950—2020年38879575篇论文的跨学科性和跨时域性的时间趋势、分布特征以及科学家的生涯演化模式进行了细致分析,并进一步研究了跨学科性、跨时域性与科学影响力的关系。研究发现:①论文的跨学科性和跨时域性呈现一致的增长趋势和不一致的领域分布;②跨学科性和跨时域性指标具有无标度分布等异质性分布特征,且跨学科性和跨时域性的相关性并不强;③科学家生涯中后期的跨学科性和跨时域性明显增强,这种趋势在很大程度上可以归因于其引用行为的变化;④跨学科性和跨时域性对科学影响力有着相反的作用效应,即跨学科性显著促进科学影响力,跨时域性显著抑制科学影响力,较强的跨学科性和较弱的跨时域性组合成为颠覆性热点论文的概率最高。本文提出的跨时域性测度框架丰富了知识融合和跨学科理论,并为科技政策和学术评价提供了启示。

基于特征拓扑融合的黑盒图对抗攻击

在大数据时代,数据之间的紧密关联性是普遍存在的,图数据分析挖掘已经成为大数据技术的重要发展趋势。近几年,图神经网络作为一种新型的图表示学习工具引起了学术界和工业界的广泛关注。目前图神经网络已经在很多实际应用中取得了巨大的成功。最近人工智能的安全性和可信性成为了人们关注的重点,很多工作主要针对图像等规则数据的深度学习对抗攻击。文中主要聚焦于图数据这种典型非欧氏结构的黑盒对抗攻击问题,在图神经网络模型信息(结构、参数)未知的情况下,对图数据进行非随机微小扰动,从而实现对模型的对抗攻击,模型性能随之下降。基于节点选择的对抗攻击策略是一类重要的黑盒图对抗攻击方法,但现有方法在选择对抗攻击节点时主要依靠节点的拓扑结构信息(如度信息)而未充分考虑节点的特征信息,文中面向引文网络提出了一种基于特征拓扑融合的黑盒图对抗攻击方法。所提方法在选择重要性节点的过程中将图节点特征信息和拓扑结构信息进行融合,使得选出的节点在特征和拓扑两方面对于图数据都是重要的,攻击者对挑选出的重要节点施加不易察觉的扰动后对图数据产生了较大影响,进而实现对图神经网络模型的攻击。在3个基准数据集上进行实验,结果表明,所提出的攻击策略在模型参数未知的情况下能显著降低模型性能,且攻击效果优于现有的方法。

期刊下载与被引次数关系及预测模型

文章以图书馆、情报与文献学CSSCI来源期刊为例,综合采用面板数据模型、面板变系数模型、面板门槛模型研究文章下载与被引之间的关系,并采用BP人工神经网络基于下载次数预测被引次数。研究表明:面板数据固定效应模型可有效分析下载次数与被引次数关系;论文被引次数主要受滞后2年的下载次数影响;不同期刊下载次数对被引次数的影响呈现趋同趋势;下载次数对被引次数的影响呈现非线性门槛特征;采用BP人工神经网络模型可以根据下载次数较好地预测被引次数;部分学科期刊可采用下载次数进行预评价,以提高评价的时效性。

中美知识融合网络与知识扩散网络对比

[研究目的]当前借助引文关系开展知识流动规律分析的研究已经十分常见,但对于知识的融合与扩散过程的研究还不够深入。从复杂网络视角分析中美学者所创造知识的流动规律有助于厘清两地的科学生产力及知识流动的差异。[研究方法]通过引用关系构建知识融合级联网络和知识扩散级联网络,采用复杂网络分析法从网络数量特征、网络结构特征和级联网络国别等特征维度对中美知识融合网络和知识扩散网络进行对比分析。[研究结论]研究发现,纯美国学者组发表文献不论是知识融合级联网络还是知识扩散级联网络规模均更大,形成的知识融合级联网络密度、接近中心性和PageRank平均数更大。物理学相比于社会学,其文献的知识融合级联网络和知识扩散级联网络呈现更加稠密、节点联系更加紧密、中心性更强的结构。本研究有助于深化对知识融合与知识扩散的认识,加深对中美两国科研生产力差异的理解。

基于局部扩展社区发现的学术异常引用群体检测

学术社交网络中的某些学者可能组成异常引用群体,相互之间过度引用彼此的文章以谋取利益。现有的异常群体检测算法大多将社区检测与节点表示学习分离,导致最终异常群体检测性能受限。为此,提出一种基于局部扩展社区发现的异常引用群体检测(GADL)算法。所提算法利用论文研究领域、标题内容等语义信息提取作者异常引用特征;定义基于节点转移相似度、节点社区隶属度、引用异常度和广度优先遍历(BFS)深度的扩展度量函数;结合异常社区发现和异常节点检测,在统一框架下对二者联合优化,可获得最优的异常检测性能。在ACM、DBLP1和DBLP2数据集上,相较于ALP算法,所提算法分别提高了6.07%、5.35%和3.38%。在真实数据集上的实验结果表明,所提算法可有效地检测异常学术引用。

基于合作与引用关系的多层网络对企业创新的影响

研究从多层网络视角剖析产学研合作关系和专利引用关系作为知识流动重要途径对企业创新的综合影响。以ICT产业为例,1 924家企业为研究对象,基于产学研合作专利和专利引用数据,通过负二项回归进行实证分析。结果表明:合作网络中自我中心网络动态性提升企业创新绩效;专利引用网络中心性在合作网络自我中心网络稳定性与创新绩效之间起中介作用,即企业可以通过维持有价值的稳定性合作关系提高其在专利引用网络的中心性来促进知识流动,进而提升创新绩效,而专利引用网络中心性在企业的合作网络自我中心网络扩张性对企业创新绩效的影响中没有起到中介作用;合作网络结构洞在专利引用网络中心性与企业创新绩效之间起负向调节作用,即企业在合作网络中结构洞水平越高,专利引用网络中心性对创新绩效的促进作用越小,而合作网络中心性在两者间没有起到正向调节作用。研究拓展了知识流动与协同创新网络的研究视角,丰富了企业创新前因变量的研究,对企业创新实践具有一定的指导意义。