2018, Vol.35, 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 propose an effective direction of data linkage for building the humanities assets one-stop portal service. For this purpose, We collected and analyzed the actual status of the domestic institution with humanities assets, and presented the linkage direction through analysis of the data held by the target organization. The results of this study are as follows: First, we proposed a classification system of humanities assets based on the reviewing the existing classification system on the subject of humanities assets. Second, we set up the categories of potential data that can be incorporated into humanities assets through a detailed analysis of the subject and type of data held by the subject institutions. Third, we analyzed the platforms of similar case organizations providing one-stop portal services for humanities assets and proposed the applicable meta fields when constructing one-stop system based on similarity.

This study examined the factors affecting the performance of automatic classification based on machine learning for domestic journal articles in the field of LIS. In particular, In view of the classification performance that assigning automatically the class labels to the articles in 「Journal of the Korean Society for Information Management」, I investigated the characteristics of the key factors(weighting schemes, training set size, classification algorithms, label assigning methods) through the diversified experiments. Consequently, It is effective to apply each element appropriately according to the classification environment and the characteristics of the document set, and a fairly good performance can be obtained by using a simpler model. In addition, the classification of domestic journals can be considered as a multi-label classification that assigns more than one category to a specific article. Therefore, I proposed an optimal classification model using simple and fast classification algorithm and small learning set considering this environment.

This research evaluated differences of classification performance for feature selection methods using LDA topic model and Doc2Vec which is based on word embedding using deep learning, feature corpus sizes and classification algorithms. In addition to find the feature corpus with high performance of classification, an experiment was conducted using feature corpus was composed differently according to the location of the document and by adjusting the size of the feature corpus. Conclusionally, in the experiments using deep learning evaluate training frequency and specifically considered information for context inference. This study constructed biomedical document dataset, Disease-35083 which consisted biomedical scholarly documents provided by PMC and categorized by the disease category. Throughout the study this research verifies which type and size of feature corpus produces the highest performance and, also suggests some feature corpus which carry an extensibility to specific feature by displaying efficiency during the training time. Additionally, this research compares the differences between deep learning and existing method and suggests an appropriate method by classification environment.