• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.19-36
• /
• 2023

As advances in information and communication technology have made it easier for anyone to produce and disseminate information, a new problem has emerged: fake news, which is false information intentionally shared to mislead people. Initially spread mainly through text, fake news has gradually evolved and is now distributed in multimedia formats. Since its founding in 2005, YouTube has become the world's leading video platform and is used by most people worldwide. However, it has also become a primary source of fake news, causing social problems. Various researchers have been working on detecting fake news on YouTube. There are content-based and background information-based approaches to fake news detection. Still, content-based approaches are dominant when looking at conventional fake news research and YouTube fake news detection research. This study proposes a fake news detection method based on background information rather than content-based fake news detection. In detail, we suggest detecting fake news by utilizing related video information from YouTube. Specifically, the method detects fake news through CNN, a deep learning network, from the vectorized information obtained from related videos and the original video using Doc2vec, an embedding technique. The empirical analysis shows that the proposed method has better prediction performance than the existing content-based approach to detecting fake news on YouTube. The proposed method in this study contributes to making our society safer and more reliable by preventing the spread of fake news on YouTube, which is highly contagious.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.166-178
• /
• 2023

This study aims to introduce and assess CNN Deep Learning methods to analyze visual landscape images on social media with embedded user perceptions and experiences. This study analyzed visual landscape images by focusing on a healing place. For the study, seven adjectives related to healing were selected through text mining and consideration of previous studies. Subsequently, 50 evaluators were recruited to build a Deep Learning image. Evaluators were asked to collect three images most suitable for 'healing', 'healing landscape', and 'healing place' on portal sites. The collected images were refined and a data augmentation process was applied to build a CNN model. After that, 15,097 images of 'healing' and 'healing landscape' on portal sites were collected and classified to analyze the visual landscape of a healing place. As a result of the study, 'quiet' was the highest in the category except 'other' and 'indoor' with 2,093 (22%), followed by 'open', 'joyful', 'comfortable', 'clean', 'natural', and 'beautiful'. It was found through research that CNN Deep Learning is an analysis method that can derive results from visual landscape image analysis. It also suggested that it is one way to supplement the existing visual landscape analysis method, and suggests in-depth and diverse visual landscape analysis in the future by establishing a landscape image learning dataset.

• The Mathematical Education
• /
• v.63 no.2
• /
• pp.165-186
• /
• 2024

Despite the growing attention on artificial intelligence-based automated scoring technology as a support method for the introduction of descriptive items in school environments and large-scale assessments, there is a noticeable lack of foundational research in mathematics compared to other subjects. This study developed an automated scoring model for two descriptive items in first-year middle school mathematics using the Random Forest algorithm, evaluated its performance, and explored ways to enhance this performance. The accuracy of the final models for the two items was found to be between 0.95 to 1.00 and 0.73 to 0.89, respectively, which is relatively high compared to automated scoring models in other subjects. We discovered that the strategic selection of the number of evaluation categories, taking into account the amount of data, is crucial for the effective development and performance of automated scoring models. Additionally, text preprocessing by mathematics education experts proved effective in improving both the performance and interpretability of the automated scoring model. Selecting a vectorization method that matches the characteristics of the items and data was identified as one way to enhance model performance. Furthermore, we confirmed that oversampling is a useful method to supplement performance in situations where practical limitations hinder balanced data collection. To enhance educational utility, further research is needed on how to utilize feature importance derived from the Random Forest-based automated scoring model to generate useful information for teaching and learning, such as feedback. This study is significant as foundational research in the field of mathematics descriptive automatic scoring, and there is a need for various subsequent studies through close collaboration between AI experts and math education experts.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.455-460
• /
• 2020

The governments of Korea, China, and Japan have operated comprehensive research institutes for railway technologies. Korea Railroad Research Institute (KRRI), China Academy of Railway Sciences Corporation Limited (CARS), and Railway Technical Research Institute (RTRI) are representatives of comprehensive railway research institutes in each country. KRRI was found to be the most advanced in the quantitative competitiveness of patents. In terms of qualitative competitiveness, KRRI has strength in civil engineering, whereas RTRI has strength in electricity. KRRI was found to have the greatest efforts in securing competitiveness in overseas property rights. By comparing the publication of papers, CARS published the most papers. On the other hand, from 2015, KRRI showed an upward trend and published the most papers. By examining the impact of the papers by the citation, KRRI was found to have higher competitiveness than the other two institutions. In the future, it will be necessary to perform big data analysis on patents and papers of the three organizations, derive the key research areas and promising technology areas for each institute, and establish a mid-to-long-term development plan for railway technology based on scientific evidence.

• Journal of Korean Home Economics Education Association
• /
• v.21 no.2
• /
• pp.45-60
• /
• 2009

This study is intended to implement an e-Learning system assisted class for the dress unit in the subject of technology & home economics in the middle school. This class is aimed at making teaching-learning in the dress unit effective, triggering students' interest in it, enhancing their understanding and offering basic materials for the e-Learning development about clothing instruction in the subject of technology & home economics. To make the concrete situational learning effective and provide realistic learning environments, learning contents were implemented so that the learners themselves could manipulate the contents by clicking. How to wear clothing according to learners' individuality was presented in order to trigger the learners' attention and motivation using the latest clothing pictures from the Internet shopping mall, and the dress fashion pictures of their peers. The result of this study can be summed up as follows. First, the implementation of learning materials with which simulation manipulation and visualization were possible could make the students reach the learning goals easily. Second, teaching-learning activity could be made more effective using audios, images and moving pictures rather than written texts. Third, learning the dress unit, which is especially related with a new fashion, made the most of the advantage of e-Learning by providing realistic and lively learning materials in a timely manner. And it triggered learners' motivation by providing pictures or moving pictures related with their real life. Based on these research results, this study suggests further research to develop e-Learning contents using various multimedia authoring tools as well as the ones applied to this study in learning the dress unit. It also suggests that the database of teaching-learning materials be constructed to securely prepare abundant instruction materials.

• Korean journal of communication and information
• /
• v.70
• /
• pp.35-65
• /
• 2015

This paper is consisted of the thesis that the decontextualized limitation of media cultural studeis in Korea should be overcome by walking into and linking with today's urban crisis and everyday life. It proposes us to become the flaneurs who do not hesitate to go to, think of, and experience actively the city in crisis under the capital/state domination. It's conclusion would be that we must practice participation observation at the fields and thus recover the critical element of cultural studies writing, by entering into the city and seeing at the features of crisis routinely expressed and symptomatically appear in there. For and before this, the author will first of all pay attention to John Fiske in later period, who was merely perceived and falsely regarded as an active audience theorist. He will also review de Certeau from whom Fiske has borrowed the concept of tactics, and Berman who has further practiced the very spatial tactic. The paper is prepared so as to expand the ideas and thoughts of them who have gone beyond the boundary of text, audience and onto the context of urban space. It's goal is much more than rescuing, recovering Fiske's alternative trajectory. It tries to reconstruct the tradition of urban media cultural studies critically connected with the dangerous, life-threatening capitalist condition. Furthermore, by filling up the theoretical vacuum left behind disconnected and cut away from Fiske, it attempts to find a vision, prospect of cultural studies that will actively engage themselves dialectally with dangerous yet hopeful life of the city and its popular masses.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.21-32
• /
• 2010

This study investigated the effects of contiguity and reading mode on cognitive load factors measured by Galvanic Skin Response(GSR). In this study two experimental conditions were imposed to participants to measure cognitive load with the high contiguity picture and low contiguity picture. Thirty-four college students participated to this experiment(experiment group=17, control group=17), and spilt-plot factorial design was applied to control individual difference in galvanic skin response. Tasks of this experiment were reading and summary. The dependent variables were skin conductance response, and perceived difficulty. The independent variables were the degree of contiguity of visual material(high contiguity vs. low contiguity). The major result of this study was identification of a significant difference of GSR with low contiguity condition. Indeed it was identified that more complex reading condition required more cognitive loads. This finding supported that different cognitive process might require different amounts of cognitive loads. For the further research, this study discussed the validity of applying physiological signals to assess cognitive loads and relationships the associated affective reactions.

• The Journal of Society for e-Business Studies
• /
• v.22 no.4
• /
• pp.141-158
• /
• 2017

Along with IT development, customers are getting more easily to express their opinions using various IT channels. In this situation, complaint management is a pressing issue for companies to acquire and maintain loyal customers with low cost. Most of previous studies have investigated customer complaint information by quantitative variables such as demographic information, transaction information, or complaint frequency, but studies focusing on qualitative aspects of complaint information are limited. Therefore, this paper considers the possibility for customers to leave even when they complain occasionally or briefly. This paper analyzes the quantitive aspects as well as the qualitative aspects using sentiment analysis with Exit-voice theory. The dataset contains 268,364 inquiries of 46,235 customers obtained from a contact center of a private security company in Korea. This paper carries out logistic regression and the results imply that the customers's explicit response and their implicit sentiment have different effect on customers leave. This study is expected to provide useful suggestions for the effective complaint management.

• Journal of the Korean Society for Library and Information Science
• /
• v.43 no.2
• /
• pp.5-28
• /
• 2009

The purpose of this study is to investigate the use of the electronic information resources of humanities scholars in Korea and propose the planning of academic library and information services to serve their needs. To collect data, a postal survey was conducted during the period of November 2007 through January 2008. Out of 799 humanities scholars sampled from 25 universities, 132 responded with a completion rate of 16%. The major findings of this study are as follows: Firstly, the majority of humanities scholars distribute their time equally between research and education, and conduct independent research. Secondly, they use, to a certain degree, electronic information resources largely in text format, and depend upon the electronic collection of their academic libraries. Thirdly, with the exception of a couple of sources of electronic journal resources, the electronic resources that these humanities scholars regularly use vary so widely that none could be considered to be a common resource. Fourthly, they value the convenience of accessing and using electronic resources, but worry about the quality and scope of the contents. It is suggested that academic libraries (1) become the gateway for the electronic information that is available both inside and outside the library, (2) provide integrated search feature for and a 'single sign on' access to electronic resources, and (3) plan customized user education for specific subject fields in the humanities.

• Journal of Korean Library and Information Science Society
• /
• v.49 no.2
• /
• pp.201-220
• /
• 2018

The purpose of this study is to explore problems within bibliotherapy research of the 15 thesis papers aimed at improving self esteem, and then to explore development plan. In the current study on bibliotherapy, the problems with bibliotherapy are presented in five aspects. First, there is a lack of professionalism and role of counselor who plays the most important role in bibliotherapy. Second, the situation of the internalizer as an internalizer of bibliotherapy was not reflected in the bibliotherapy program. Third, the lack of diversity in the bibliotherapy program does not keep the reader's interest in bibliotherapy. Fourth, bibliotherapy reading material is limited to text material, which lacks the use of various media. Fifth, there is insufficient validity for the test paper that measures the effectiveness of the reader's bibliotherapy in terms of research methods. Several development plan are proposed based on the factors that affect bibliotherapy. First, it is necessary to develop and train teaching materials to secure expertise of bibliotherapy counselors. Second, it is necessary to develop data on the various media on suitable for bibliotherapy material. Third, it is necessary to review the test paper that can accurately measure the effectiveness of bibliotherapy.