|
Title Information Classification Based on Hownet Semantics Feature Extension
Li Xiangdong, Liu Kang,Ding Cong, Liao Xiangpeng
LIBRARY JOURNAL. 2017, 36 (2): 11-19.
This paper uses the internal semantic relevance of the text and get the core semantic word set of the training text through high frequency words and the hidden theme. It then use the Hownet as an external resource to calculate the similarity between the core semantic word set and testing text. It extends
the keywords in training text, whose similarity is greater than a certain level, into the testing text, and classifies them with SVM. The result shows that in the case where training set and test set are only titles,and there are 200 pieces in each category of training set, there is an increase of efficiency to 3.1%; but the
efficiency declines with the increase of the number of training set text over 200. In the case where training sets are titles and abstracts whereas the testing sets are titles, the classification algorithm put forward in this paper could achieve 1.5% and 3.1% on Macro_F1in Fudan corpus and the self-builtjournal corpus, and 2.3% and 5.3% on Micro_F1. This paper aims to implement characteristic extension of journal titles with sparse characteristics in the hope of improving the work of title classification.
References |
Related Articles |
Metrics
|
|
The Analysis of Information Science Research Hot Topics in China between 2006 and 2016 based on Strategy Coordinate Diagram
Li Qianqian
LIBRARY JOURNAL. 2017, 36 (2): 29-34.
We took CNKI as the data source, extracted the key words from doctoral and master’s papers collected by CNKI during 2006 and 2016, and analysed them. Firstly, we found the high frequency keywords by using EXCEL, and constructed the high frequency keywords matrix and Salton matrix. We then put the Salton matrix to SPSS to do cluster analysis by calculating the adhesiveness value to determine each group's core research topic. Finally, we constructed the strategy coordinate diagram, and analysed the current situation of information science’s hot topics in China for the specified decade. We found that,
among the eight hot topics, the “Competitive Intelligence Analysis”, “Knowledge Management”, “Social Network Analysis” and “Information Service under the Network Environment” are the key research topics and that information science research in this decade is following closely the development of the information age.
References |
Related Articles |
Metrics
|
|
The Social, Political and Legal Aspects of Text and Data Mining (TDM)
Liu Jingjing
LIBRARY JOURNAL. 2017, 36 (2): 35-39.
The ideas of textual or data mining (TDM) and subsequent analysis go back hundreds, if not thousands, of years. Originally carried out manually, textual and data analysis has long been a tool enabling new insights drawn from text corpora. However, for the potential benefits of TDM to be unlocked,
a number of non-technological barriers need to be overcome. These include legal uncertainty resulting from complicated copyright, database rights and licensing, the fact that some publishers are not currently embracing the opportunities TDM offers for the academic community, and a lack of awareness of TDM among many academics, alongside a gap of skills.
References |
Related Articles |
Metrics
|
|
Study on the Functional Requirements and Space Design of Modern Library Reading Space
Song Xiaodan, Zhu Kongguo,Li Xueyin, Li Sheng
LIBRARY JOURNAL. 2017, 36 (2): 70-73.
With the development of information technology and the transformation of library services concept, the modern library reading space is showing a variety of functional requirements. This paper analyzes these functional requirements of reading space from three aspects, namely, resources, readers and services, and expounded different types of libraries reading space design, mainly including paper document collecting-reading space, digital resource reading space, and privacy reading spacelearning commons, leisure reading space and publicity exhibition space. It aims to further the library service from the perspective of reading space design.
References |
Related Articles |
Metrics
|
|
Construction and Application of Urban Public Library Layout Visualization System
Xu Xin, Qian Jiayi
LIBRARY JOURNAL. 2017, 36 (2): 87-94.
The paper reviews the studies about the layout of public libraries and discusses the factors that influence the layout and standards of the layout. Based on these, the paper designs and builds a visualization system for city public library layout, which shows the layout of libraries at different levels,
displays information such as the size, address, telephone number, open hours, and feature collections. And the system is capable of generating a map based on population information which enabled users to discover the shortcomings in the layout of city public libraries. The paper also takes Shanghai as an example, and conducts a visualization analysis of its present library layout. With the help of a field study, the paper gives out some suggestion on improvements.
References |
Related Articles |
Metrics
|
|
Research and Implementation of Data Integration Approach Based on Semantic Query Interface in the Scientific Research Ontology Knowledge Base
Tang Yijie, Liu Yi,Song Wen, Zhou Zijian,Yang Rui, Li Jianwei
LIBRARY JOURNAL. 2017, 36 (2): 95-102.
In order to organize major resources of the domestic and foreign research areas into the Scientific Research Ontology Knowledge Base, the paper proposes the study and discussion of data integration methods. Firstly, it describes the idea of data integration methods from three aspects, includes data
standardized templates, data re-check strategy and development of integrated tools. On this basis, it focuses on the key technical points of the data integration to complete the process. Finally, data integration methods are tested and their feasibility and operability validated. It also proposes future research priorities.
References |
Related Articles |
Metrics
|
|