|
A Comparative Study of Relevant Classification Techniques in Automatic Classification for Two Categories with Similar Contents: Taking E271 and E712.51 in the Chinese Library Classification as Example
Li Xiangdong, Ruan Tao
Libraly Journal. 2018, 37 (6): 11-20.
The purpose of this paper is to study the automatic classification (two types of classification) based on machine learning in two categories with very similar contents in the Chinese Library Classification. In this paper, we use the bibliographic information of E271 and E712.51 as two types of bibliographic information, and provide a comparative study of the performance of some representative technologies, three feature selection methods, namely, CHI, IG and MI, two feature weighting methods, namely, TF and TF * IDF, and three classification algorithm, namely, KNN, NB and SVM, in the classification of two categories, which provides basic data for targeted automatic classification research. The experimental results show that the performance of CHI and IG is better than MI. However, when the number of features of MI are more than 4000, the performance is improved enormouslyly. For the classification algorithm, the performance of the NB, which adopts the MI feature selection, is the best. The performance of the SVM is better, which uses the feature selection of CHI and IG, than NB and KNN. And the KNN is worse than the former. For feature weighting, TF is better than TF * IDF in most cases. However, the performance of feature weighting is easily influenced by the classification algorithm, the number of features or feature selection method. The related technology in each classification can be combined to adapt to the automatic classification of imitation classification, but the performance of related methods have different advantages and disadvantages, which needs to further improve the classification of related technology and to further improve the classification of similar categories to carry out automatic classification of performance.
References |
Related Articles |
Metrics
|
|
An Empirical Analysis on Library Anxiety: A Case Study of National Library of China
Yang Jing
Libraly Journal. 2018, 37 (6): 52-55.
National Library of China is a national library with the character of a public library which provides reading services to general public. Library anxiety has negative effects on the effective use of library. Through the analysis on the overall level of readers’ library anxiety and its influencing factors, the librarian has a better understanding of readers’ reading experiences, in order to enhance the quality of services. Through questionnaires, this study analyses readers’ anxiety in 7 aspects: library regulations, librarian, comfort of library, the library convenience, the quality of library resources, knowledge of library, and emotion. The result shows that readers’ library anxiety is on a moderate to minor level. Factors such as readers’ age, education, the frequency and purpose of library usage are related to the level of reading anxiety. Based on the results, this study provides some suggestions and recommendation that can be used for easing readers’ anxiety.
References |
Related Articles |
Metrics
|
|
The Advantages and Development Direction of the Public Library Service Alliance: Taking the Public Library Service Alliance of Zhengzhou as an Example
Yang Lin
Libraly Journal. 2018, 37 (6): 62-68.
During the development of modern public cultural service system and while promoting nationwide reading, public library service alliance plays an irreplaceable role in the standardization of public cultural service, equalization and diversity. The public library service alliance in Zhengzhou, for example, enabled the digital resource sharing, one card for city-wide libraries, free provision of resources and technology for branch libraries, and learning mechanism within the circle. Taking the Alliance in Zhengzhou as an example, this paper discusses the advantages of public library service alliance, and points out the development direction of such alliances in China.
References |
Related Articles |
Metrics
|
|
Reading Anxiety: Connotation, Category, Origin and Principle
Yang Chen
Libraly Journal. 2018, 37 (6): 85-89.
In the Internet era, the new information technology detonates the reading revolution, whereas the reading crisis causes the reading anxiety. By defining the concept of reading anxiety, distinguishing the types, tracing back to the origin and exploring the principles, this paper tries to present the overall situation of reading anxiety, so as to call for attention from academic circle and libraries for study and treatment, and to provide new ideas and theoretical guidance for library to innovate reading promotion service.
References |
Related Articles |
Metrics
|
|
Correcting the Name and Courtesy Name of the Northern Dynasty Scholar of Confucian Classics Fan Shen
Yang Hongsheng
Libraly Journal. 2018, 37 (6): 113-116.
The Rulin biographies in Book of Zhou and History of Northern Dynasties both recorded that the famous scholar of Confucian Classics in the Northern Dynasties, Fan Shen, has “Name of Shen, Courtesy Name of Wenshen”, which is widely followed. Book of Sui: Classics & Culture Works called him as Fan Wenshen directly, Old Book of Tang: Classics & Culture Works and New Book of Tang: Art & Literature Works also did so. In ancient books and literatures in Wei, Jin, Northern and Southern Dynasties, the meaning of Wenshen is not beautiful, using such name is not in accordance with the ancient’s routine of naming. As a matter of fact, his actual courtesy name is Wenyuan, which still can be found in The Primary Anthology and Taiping Imperial Encyclopedia, etc., those books usually copy from old one by conventionality. Book of Zhou and History of Northern Dynasties both recorded it as Wenshen is because of Emperor Gaozu Li Yuan, where the word “Yuan” shall be avoided as taboo. According to Book of Sui, Zhou Guangye in the Qing Dynasty thought his name was Yuan and the courtesy name was Wenshen, which is completely a word of assumption.
References |
Related Articles |
Metrics
|
|