需求驱动下高校图书馆智慧信息服务平台设计研究

论文从需求驱动知识流动这一视角出发,构建了高校图书馆内用户与机器、用户与馆员,用户与资源的三种知识流动的组合结构模型,同时在分析智慧信息服务价值特征的基础上设计了高校图书馆智慧信息服务平台的总体结构,旨在为高校图书馆智慧变革提供借鉴。     

Identification of highly-cited papers using topic-model-based and bibliometric features: the consideration of keyword popularity

The number of received citations have been used as an indicator of the impact of academic publications. Developing tools to find papers that have the potential to become highly-cited has recently attracted increasing scientific attention. Topics of concern by scholars may change over time in accordance with research trends, resulting in changes in received citations. Author-defined keywords, title and abstract provide valuable information about a research article. This study performs a latent Dirichlet allocation technique to extract topics and keywords from articles; five keyword popularity (KP) features are defined as indicators of emerging trends of articles. Binary classification models are utilized to predict papers that were highly-cited or less highly-cited by a number of supervised learning techniques. We empirically compare KP features of articles with other commonly used journal-related and author-related features proposed in previous studies. The results show that, with KP features, the prediction models are more effective than those with journal and/or author features, especially in the management information system discipline.     

Robust parameterisation of ages of references in published research

The purpose of this research is to illustrate the use of the gamma distribution to model the ages of references in published research, and to demonstrate that the two gamma distribution parameters characterise a field of research in a manner that is complementary to and more nuanced than the Price Index or mean age of references.Minimum Distance Estimation is shown to produce robust estimates of the gamma distribution parameters because of the insensitivity of the Kolmogorov–Smirnov test in the tails of the distribution.Using a sample of 816 articles from 26 different journals across six subject areas, it is shown that the gamma distribution is at least as good as a lognormal distribution to model the ages of references in research articles.The two gamma distribution parameters indicate the rate of publication of new knowledge within the respective discipline and the citing behaviour in terms of the recency of references. Interpretation of these gamma distribution parameters enables a more nuanced and granular interpretation of the distinctiveness of disciplines, sub-disciplines, formats of publication and the distribution of references within articles than possible using the Price Index, half-life or mean age of references.     

Knowledge spillovers: Does the geographic proximity effect decay over time? A discipline-level analysis,accounting for cognitive proximity,with and without self-citations

This work analyzes the variation over time of the effect of geographic distance on knowledge flows. The flows are measured through the citations exchanged between scientific publications, including and excluding self-citations. To calculate geographic distances between citing and cited publication, each publication is associated with a “prevailing” territory, according to the authors’ affiliations. We then apply a gravity model to account for the research size of the territories, in terms of cognitive proximity of citing-cited publications. The field of observation is the 2010–2017 world publications citing the 2010–2012 Italian publications, as indexed in the Web of Science. The results show that in domestic knowledge flows, geographic proximity remains an influential factor through time, although with differences among disciplines and trends of attenuating effects. Finally, we replicate the analyses of knowledge flows but with the exclusion of self-citations: in this manner the effect of geographic proximity seems reduced, particularly at the national scale, but the differences (with vs without self-citations) lessen through time. As shown in previous works, the effect of distance on continental flows is modest (imperceptible for intercontinental flows), yet here too time has some influence, including concerning exclusion of self-citations.     

Effect of class imbalance in heterogeneous network embedding: An empirical study

Network science has been extensively explored in solving various bibliometrics tasks such as Co-authorship prediction, Author classification, Author clustering, Author ranking, Paper ranking, etc. While majority of the past studies exploit homogeneous bibliographic network (consists of singular type of nodes and edges), in recent past there is a surge in using heterogeneous bibliographic entities and their inter-dependencies using heterogeneous information networks (HIN). Unlike homogeneous bibliographic networks, a bibliographic HIN consists of multi-typed nodes such as Author, Paper, Venue, etc. and corresponding relations. Thus bibliographic HIN is more complex and captures rich semantics of underlying bibliographic data as well as poses more challenges. Since a real-world HIN may have different number of instances for different node types, class imbalance is ubiquitous. Recent studies discuss class imbalance in brief and exploit meta-path-based strategies to address the issue. However, there is no work which quantitatively study the effect of class imbalance in regards to solving real-world bibliometrics tasks. Therefore, this paper first proposes a metric to estimate class imbalance in HIN and study the effects of class imbalance over two bibliometrics tasks, namely (i) Co-authorship prediction and (ii) Author's research area classification, using node features generated by network embedding-based frameworks for DBLP dataset. From various experimental analysis, it is evident that class imbalance in bibliographic HIN is an inherent characteristic and for better performance of the above-mentioned bibliometrics tasks, the bibliographic HINs must consider Author, Paper, and Venue as node types.     

中文电子病历的分词及实体识别研究

[目的/意义]健康医疗大数据是我国重要的基础性战略资源，本研究对中文电子病历分词与实体识别的探讨与实证较好地完成了医疗数据的信息抽取任务，对今后医疗大数据在语义层面的应用发展具有重要意义。[方法/过程]本研究首先融合权威词表、官方标准、健康网站数据及其他医学补充词库构建了词语数量级达到10万的医学词表；然后对电子病历的字段进行分词，对比了jieba工具、导入词典后的jieba、无监督学习及AC自动机4种模型的分词效果；最后，以自动分词和人工标注结果为语料，实现基于条件随机场的电子病历实体识别研究，并比较不同实体类别以及不同文本特征下的实体识别效果，选出最优模板。[结果/结论]分词结果显示，AC自动机的效果最好，F值可达82%；实体识别结果表明，"检查"和"疾病"实体的识别效果最好，而"症状"的识别效果不太理想。     

美国民俗生活中心口述文献的采集与利用

[目的/意义]推动我国图书馆的口述文献采集工作，提升我国图书馆口述文献利用服务水平。[方法/过程]通过网络、文献、邮件等方式，对美国国会图书馆下属的美国民俗生活中心进行全面调研，对其开展的退伍军人历史、职业民俗、民权口述历史调查和洛马克斯家族等典型项目进行介绍总结，在此基础上分析该中心开展口述文献采集与利用的经验。[结果/结论]分析结果认为，该中心积极利用数字技术与平台、探索多元化采集模式、加强与社会组织合作、设立各种基金与倡导捐款、尊重参与者合法权益等做法和经验，对我国图书馆界具有一定的借鉴意义。