Constructing linkage between libraries and up-to-date news. Issue 2 (20th June 2016)

• Record Type: Journal Article
• Authors: Yu, Wei; Chen, Junpeng
• Is Part Of: Library hi tech. Volume 34:Issue 2(2016)
• Page Start: 301
• Page End: 313
• Publication Date: 2016-06-20
• Subjects: Library services -- Web resources -- Information technologies -- Libraries resources recommendation -- Up-to-date news -- WMF; Library science -- Technological innovations -- Periodicals; Libraries -- Automation -- Periodicals; Information science -- Periodicals; 025.00285
• DOI: 10.1108/LHT-11-2015-0109
• Languages: English
• ISSNs: 0737-8831

Abstract

Abstract : Purpose: – The purpose of this paper is to construct the linkage between libraries and up-to-date news. This study developed a system to recommend libraries' resources to those daily news readers who are interested in the topics of the target news. The analysis of experiments results served as the reference for the development and improvement of linking libraries' resources with other web resources. Design/methodology/approach: – Up-to-date news were gathered through the news feeds to make the integration with the libraries' records. In task 1, the libraries' records were linked and recommended to the target libraries' records which are of the same topics. In task 2, the system aimed to find the relevant libraries' records for target news. Three recommendation methods were compared in both tasks to find the most effective approach to the system. Findings: – Experiment results showed that: at first, in task 1, the system can assign the libraries' records of the related topics effectively; second, in task 2, the recommending system can obtain a satisfied recall hit rate through human evaluation. Therefore, regarding the popularity of the daily news online, the linkage and recommendation with the libraries' resources can increase the visibility of the libraries' resources and eventually promote the information consuming in libraries. Practical implications: – The authors have confirmed, using three matrix factorization methods, that weighted matrix factorization used in the libraries' records recommendation system, could achieve better performance than the other two. Based on the research, the libraries could incorporate the online news and libraries' resources in practice. Originality/value: – To increase the visibility and promote information consuming of libraries, this study proposed a novel method to construct the linkage between library and up-to-date news. The results of data analysis indicate that recommendation of libraries resources through the daily news can achieve effective performance. Thus, it can be inferred that the research results of this study are representative and have practical values in real world practice.