• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.449-452
• /
• 2023

The rapid development of the Internet has led to a significant increase in multimedia content in social networks. How to better analyze and improve video classification models has become an important task. Deep learning models have typical "black box" characteristics. The model requires explainable analysis. This article uses two classification models: ConvLSTM and VGG16+LSTM models. And combined with the explainable method of LRP, generate visualized explainable results. Finally, based on the experimental results, the accuracy of the classification model is: ConvLSTM: 75.94%, VGG16+LSTM: 92.50%. We conducted explainable analysis on the VGG16+LSTM model combined with the LRP method. We found VGG16+LSTM classification model tends to use the frames biased towards the latter half of the video and the last frame as the basis for classification.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.20 no.3
• /
• pp.129-147
• /
• 2009

The ultimate goal of classification systems is to provide tools for information management and services through collocation of information objects in similar topics. The National Research Council for Economics, Humanities, and Social Sciences(NRCS) aims to organize the research products from 23 research institutes. To manage and organize the research products effectively, the standard classification system has been developed in conjunction of users' survey and the Business Reference Model(BRM). Although the standard classification system consists of users' perspectives and the aspects of organizational functions, there are limits to apply the system into classification practices. In this study, the proposed hybrid approach is to combine a clustering approach with 1,884 keywords from the titles of research products between 2007 and 2008. The clustering approach is performed in a heuristic way according to the KDC due to the lack of digital full texts of research products. The results of this study proposed a revised standard classification system for NRCS with 16 headings and 90 sub-headings. The revised standard classification system will play an important role in managing research products effectively.

• Journal of the Korean Society for information Management
• /
• v.37 no.1
• /
• pp.1-21
• /
• 2020

This study applied automatic classification using table of contents (TOC) text for 6,253 social science books from a newly arrived list collected by a university library. The k-nearest neighbors (kNN) algorithm was used as a classifier, and the ten divisions on the second level of the DDC's main class 300 given to books by the library were used as classes (labels). The features used in this study were keywords extracted from titles and TOCs of the books. The TOCs were obtained through the OpenAPI from an Internet bookstore. As a result, it was found that the TOC features were good for improving both classification recall and precision. The TOC was shown to reduce the overfitting problem of imbalanced data with its rich features. Law and education have high topic specificity in the field of social sciences, so the only title features can bring good classification performance in these fields.

• Journal of the Korean Society for information Management
• /
• v.38 no.2
• /
• pp.227-250
• /
• 2021

This study analyzed humanities and social science (HSS) journals of KCI to examine the multidisciplinarity and interdisciplinarity in the general and miscellaneous fields (hereinafter referred to as 'GM fields'), The multidisciplinarity and interdisciplinarity identified in this study will be a foundation to improve classification of KCI journals in GM fields. Each journal's multidisciplinarity and interdisciplinarity were measured by journal-level entropy and document-level entropy, respectively, in the citation relationships. According to the analysis, GM field journals have wide ranges of multidisciplinarity and interdisciplinarity. To improve classification quality of journals in GM fields, the general humanities should be considered as a new classification class for the multidisciplinary and interdisciplinary journals in the humanities. Furthermore, this study proposes a strategy to reclassify GM field journals of HSS according to their multidisciplinarity and interdisciplinarity.

• Journal of People, Plants, and Environment
• /
• v.24 no.6
• /
• pp.663-672
• /
• 2021

Background and objective: As the 'Healing Agriculture Research and Development and Promotion Act' came into effect on March 25, 2021, social interest in agro-healing has been increasing exponentially. This study was conducted to analyze the priorities of agro-healing classification system and to provide basic data to inform policy directions and related research for the development and activation of agro-healing. Methods: The survey data collected from 18 experts were analyzed using the analytic hierarchy process (AHP) method in determine the relative weights of the main and sub-criteria for the classification system. There were three main criteria identified: agro-healing input industry, agro-healing service industry, and agro-healing-related/derived industry. There were also 11 sub-criteria. Results: The top three sub-criteria with the highest complex weights include "community service," "social rehabilitation" and "treatment and rehabilitation," all of which correspond to the main criterion "agro-healing service industry". In addition, the complex weights of the sub-criteria corresponding to the main criterion "agro-healing related/derived industry" are as follows: "other agro-healing support service," which ranked 4th, and "training and education institutions for agro-healing experts," which ranked 5th when prioritizing the criteria. Conclusion: The results of this study suggest that the main criterion to be considered first in establishing a classification system is "agro-healing service industry". Therefore, it is necessary to continue research on detailed service classifications and systems with verified validity to ensure expertise in human resources, and organization related to social purpose services in agro-healing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.370-396
• /
• 2024

COVID-19 was declared a pandemic by the World Health Organization (WHO) on 30 January 2020. The lifestyle of people all over the world has changed since. In most cases, the pandemic has appeared to create severe mental disorders, anxieties, and depression among people. Mostly, the researchers have been conducting surveys to identify the impacts of the pandemic on the mental health of people. Despite the better quality, tailored, and more specific data that can be generated by surveys,social media offers great insights into revealing the impact of the pandemic on mental health. Since people feel connected on social media, thus, this study aims to get the people's sentiments about the pandemic related to mental issues. Word Cloud was used to visualize and identify the most frequent keywords related to COVID-19 and mental health disorders. This study employs Majority Voting Ensemble (MVE) classification and individual classifiers such as Naïve Bayes (NB), Support Vector Machine (SVM), and Logistic Regression (LR) to classify the sentiment through tweets. The tweets were classified into either positive, neutral, or negative using the Valence Aware Dictionary or sEntiment Reasoner (VADER). Confusion matrix and classification reports bestow the precision, recall, and F1-score in identifying the best algorithm for classifying the sentiments.

• The Journal of Korean Society for School & Community Health Education
• /
• v.6
• /
• pp.117-126
• /
• 2005

This study attempted to extract a suggestive point to help the design of a program, which is used to promote physical activities, by applying a social cognitive theory based on literature review on the physical activity based on a social cognitive theory. This study considers 10 journal articles that used a social cognitive theory, physical activity, and exercise as the major variable using the EBSCOhost Academic Search Premier and Educator's Reference Desk (ERIC). The type of papers was analyzed using a certain criterion, which can be configured according to the number of each year's papers, characteristics of research subjects, application type of a social cognitive theory, and classification of the application of objects in a social cognitive theory. The characteristics of each year's papers presented no specific characteristics for each year's papers, but the study in 2004 especially presented a high level. The characteristics of research subjects presented four highest cases in the case of the college student, and there were zero cases for children. The application type of studies on physical activities using a social cognitive theory can be largely classified as three types. The results of the measurement using a sectional investigation for SCT objects were 2 cases, the application of SCT for promoting physical activities was 1 case, and the demonstration of evaluation for the effect of SCT objects presented 8 highest cases. Although the social cognitive theory in the characteristics of the classification of object applications can be classified as 10 objects, there were no cases that used 10 all objects, partial applications of the object were measured in 8 studies, and two cases presented no detailed considerations on the object. Most of studies used a part of the object where the application of self-efficacy were measured by 8 highest cases. In addition, there were no measurements on the situation, observation learning, answer and response, and self-management. The elements of attitude, cognitive activity, self-efficacy, and handicaps among the SCT object were commonly used, and studies that the self-efficacy largely affects on the promotion of physical activities presented the main current.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.826-833
• /
• 2009

Currently, the rise of social tagging has changing taxonomy to folksonomy. Tag represents a new approach to organizing information. Nonhierarchical classification allows data to be freely gathered, allows easy access, and has the ability to move directly to other content topics. Tag is expected to play a key role in clustering various types of contents, it is expand to network in the common interests among users. First, this paper determine the relationships among user, tags and resources in social tagging system and examine the circumstances of what aspects to users when creating a tag related to features of websites. Therefore, this study uses tags from the social bookmarking service 'del.icio.us' to analyze the features of tag words when adding a new web page to a list. To do this, websites features classified into 7 items, it is known as tag classification related to resources. Experiments were conducted to test the proposed classify method in the area of music, photography and games. This paper attempts to investigate the perspective in which users apply a tag to a webpage and establish the capacity of expanding a social service that offers the opportunity to create a new business model.

• Journal of the Korean Society for Library and Information Science
• /
• v.34 no.1
• /
• pp.71-92
• /
• 2000

This study aims to content analysis of Library Classification System in the North Korean. Also This paper is analyze and overview to conceptual framework. Notational system. Principle of hierarchy in the North Korean's Library Classification System. Libraries usually arrange their collections according to the systematic structure of the library classification. A decimal point follows the third digit. After which division by ten continues to the specific degree of classification needed. This system is based on the social and communism thought. The libraries in the South and the North has different concepts, goals, information resources, classification system and the different ways of using them. Considering the practical aspects of the libraries and the reasons for their existence, they must structure the mutual cooperative system so as to minimize the shock when confronting the social changes, so-cold the national unification.

• Korea journal of population studies
• /
• v.25 no.2
• /
• pp.193-230
• /
• 2002

Issues regarding "generation" are facing a renaissance during recent years. One of prevailing reasons for this development is the crisis of collective identities due to diverse contemporary socio-political circumstances and cultural characteristics of Korean society. However, it is often criticized that the sociological examination of this topic is rather in a obscure stage resulting from the inherent confusion and ambiguities mainly caused by the mixed usage of the concept. In this regard, this study explores the possibility of answering these critics and refining the systemic usage for the sociology of generation in the realm of social changes and social innovations. For this purpose, analytical classification of the concept based on various contextual typology are attempted.attempted.