2019, Vol.36, No.2

Journal of the Korean Society for Information Management 2023 KCI Impact Factor : 1.31

pISSN : 1013-0799 / eISSN : 2586-2073
https://journal.kci.go.kr/kosim

The purpose of this study is to investigate the status of specialized services, user experience, and the overall satisfaction for the specialized library users, and based on the ISA method, compare the specialized theme data, specialized service place, specialized program, specialized theme area facilities and environment, and derive issues of the specialized library operation and improvement measures. Consequently, first, when selecting the theme of the specialized library, the theme ought to be selected to reflect the regional characteristics, history and demographics of the library, and the demand survey of the local residents and library users would need to be considered. Second, when planning the specialized program, the specialized library ought to consider operating differentiated programs based on the program operator who has the expertise to improve the quality of the program. Furthermore, sufficient theme related books and space must be secured, and moreover, the program must be planned in connection with the book collection. Third, the specialized library should be so structured as to ensure that the space may serve specialized themes provided by the library in order to provide specialized collections, services, and information services for the users. In addition, reflecting the needs of the users in designing the space must be considered.

The user satisfaction and needs of an academic library were caught through a questionnaire survey in this study. The aim of this study is to draw up the CRM based plan for meeting user needs on the study. The users’ demographic information, library resources & their use, homepage, services, and facilities/environment of the library were categorized in the questionnaire and analyzed for this study. The major conclusions of this study are: ⑴ The library resources use was the highest, and its facilities/environment was the lowest in the user satisfaction study. It also revealed that there are much necessities for the quick acquisition and dissemination of the requested material to the library users, and for the inter-library loan (ILL) services among campuses for the subscription books in the library resources use study, too; ⑵ There are a lot of necessities for the improvement of OPAC retrieval and the subscription books system, and menu rearrangement in the library homepage; ⑶ There are a lot of necessities for the plans of more frequent library event, more detailed event guidance, and more reinforcement of public relations such as SMS, push services of SDI etc. in the library user services; and ⑷ There are a lot of necessities for the improved policies to the complaints of library users such as the lack of common study place and lockers, air conditioning and heating problem, complaints about facilities management of restroom (lack of toilet paper), library accessibility on campus, unauthorized user management etc. in the facilities/environment of the library.

Random Forest (RF), a representative ensemble technique, was applied to automatic classification of journal articles in the field of library and information science. Especially, I performed various experiments on the main factors such as tree number, feature selection, and learning set size in terms of classification performance that automatically assigns class labels to domestic journals. Through this, I explored ways to optimize the performance of random forests (RF) for imbalanced datasets in real environments. Consequently, for the automatic classification of domestic journal articles, Random Forest (RF) can be expected to have the best classification performance when using tree number interval 100〜1000(C), small feature set (10%) based on chi-square statistic (CHI), and most learning sets (9-10 years).