• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.87-94
• /
• 2024

We investigated the feasibility of utilizing Large Language Models (LLMs) to perform text-based games without training on game data in advance. We adopted ChatGPT-3.5 and its state-of-the-art, ChatGPT-4, as the systems that implemented LLM. In addition, we added the persistent memory feature proposed in this paper to ChatGPT-4 to create three game player agents. We used Zork, one of the most famous text-based games, to see if the agents could navigate through complex locations, gather information, and solve puzzles. The results showed that the agent with persistent memory had the widest range of exploration and the best score among the three agents. However, all three agents were limited in solving puzzles, indicating that LLM is vulnerable to problems that require multi-level reasoning. Nevertheless, the proposed agent was still able to visit 37.3% of the total locations and collect all the items in the locations it visited, demonstrating the potential of LLM.

• Communications of Mathematical Education
• /
• v.38 no.2
• /
• pp.231-246
• /
• 2024

In this paper, we present the development and a case study on 'Mathematics & Coding Mobile Contents' tailored for secondary education. These innovative resources aim to alleviate the burden of laborious calculations, enabling students to allocate more time to engage in discussions and visualize complex mathematical concepts. By integrating these contents into the curriculum, students can effectively meet the national standards for achievement in mathematics. They are empowered to develop their mathematical thinking skills through active engagement with the material. When properly integrated into secondary mathematics education, these resources not only facilitate attainment of national curriculum standards but also foster students' confidence in their mathematical abilities. Furthermore, they serve as valuable tools for nurturing both computational and mathematical thinking among students.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.4
• /
• pp.33-49
• /
• 2019

The purpose of this study was to investigate the changes in the experiences of visitors of Yeonnam-dong during the period covering the development of a linear park, the Gyeongui Line Park. This study used a text mining technique to analyze Naver Blog postings of those who visited Yeonnam-dong from June 2013 to May 2017, divided into four periods -from June 2013 to May 2014, from June 2014 to May 2015, from June 2015 to May 2016 and from June 2016 to May 2017. The keywords used were 'Yeonnam-dong', 'Gyeongui Line' and 'Yeontral Park' and the data was further refined and resampled. A semantic network analysis was conducted on the basis of the co-occurrences of words. The results of the study were as follows. During the entire period, the main experience of visitors to Yeonnam-dong was 'food culture' consistently, but the activities related to 'market', 'browsing', and 'buy' increased. Also, activities such as 'walk', 'play' and 'rest' in the park newly appeared after the construction of the park. Moreover, more diverse opinions about the Yeonnam-dong were expressed on the blog, and Yeonnam-dong began to be recognized as a place where a variety of activities can be enjoyed. Lastly, when the visitors wrote about the theme 'food culture', the scope of the keywords expanded from simple ones, such as 'eat', 'photograph' and 'chatting' to 'market', 'browsing', and 'walk'. The sub-themes that appeared with the park also expanded to various topics with the emergence of the Gyeongui Line Book Street. This study analyzed the change of experiences of visitors objectively with text mining, a quantitative methodology. Due to the nature of text mining, however, the subjective opinions inevitably have been involved in the process of refining. Also, further research is required to assess the direct relationship between these changes and park construction.

• Journal of Digital Contents Society
• /
• v.19 no.5
• /
• pp.981-993
• /
• 2018

Smart healthcare is convergence of ICT and healthcare services, and interdisciplinary research has been actively conducted in various fields. The objective of this study is to investigate trends of smart healthcare research using topic modeling and ego network analysis. Text analysis, frequency analysis, topic modeling, word cloud, and ego network analysis were conducted for the abstracts of 2,690 articles in Scopus from 2001 to April 2018. Topic Modeling analysis resulted in eight topics, Topics included "AI in healthcare", "Smart hospital", "Healthcare platform", "Blockchain in healthcare", "Smart health data", "Mobile healthcare", " Wellness care", "Cognitive healthcare". In order to examine the topic modeling results core deeply, we analyzed word cloud and ego network analysis for eight topics. This study aims to identify trends in smart healthcare research and suggest implications for establishing future research direction.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.2
• /
• pp.367-375
• /
• 2021

This study aimed to identify the knowledge structure of researches on 'untact' and derived implications for directions for the studies using text mining. The study included network analysis and topic modelling of keywords and abstracts from 171 thesis published until October 2020. Centrality analysis showed that 'untact' studies had been focused on service, usage, consumption, technology and online. From the topic modelling, 6 topics such as 'COVID-19 and socio-technological change', 'needs and utilization of education contents', 'technology and service for user convenience', 'product marketing and sales', 'service design of the company', 'influence factors of usage and consumption' were extracted. Keywords that connect each topic were technology, service, usage, consumption, needs and factor. Exploratory analysis of 'untact' researches using text mining provides useful results for development of 'untact' studies.

• Journal of Digital Convergence
• /
• v.21 no.2
• /
• pp.9-16
• /
• 2023

The purpose of this study is to analyze research trends on ESG (Environmental, Social, and Governance), and to present a direction for companies and investors to use ESG information. To this end, text mining, one of the atypical data mining techniques, was used for analysis. Thesis abstracts from January 2014 to February 2023 were collected from the SCOPUS database, and Economics, Econometrics and Finance were the most common. The United States and China published the most ESG papers, and Korea published the 6th most papers in the world. This study is meaningful in that it analyzed the main research trends of ESG using text mining techniques such as LDA and topic modeling. It was confirmed that ESG is being conducted in various fields, not in a specific field, and it is differentiated from previous studies in that it analyzed various influencing factors and ripple effects of ESG.

• Journal of Internet Computing and Services
• /
• v.17 no.5
• /
• pp.151-160
• /
• 2016

The purpose of this research is to investigate Korean popular attitudes and social perceptions of 'sharing economy' terminology at the current moment from a creative or socio-economic point of view. In Korea, this study discovers and interprets the objective and tangible annual changes and patterns of sociocultural collective intelligence that have taken place over the last five years by applying text mining in the big data analysis approach. By crawling and Googling, this study collected a significant amount of time series web meta-data with regard to the theme of the sharing economy on the world wide web from 2010 to 2014. Consequently, huge amounts of raw data concerning sharing economy are processed into the value-added meaningful 'word clouding' form of graphs or figures by using the function of word clouding with R programming. Till now, the lack of accumulated data or collective intelligence about sharing economy notwithstanding, it is worth nothing that this study carried out preliminary research on conducting a time-series big data analysis from the perspective of knowledge management and processing. Thus, the results of this study can be utilized as fundamental data to help understand the academic and industrial aspects of future sharing economy-related markets or consumer behavior.

• Journal of Technology Innovation
• /
• v.21 no.2
• /
• pp.25-56
• /
• 2013

As science and technology are emphasized as national competitiveness, major nations designate new growth engine industry and establish the effective investment and the development strategy to enhance industrial development and competitiveness through science and technology. New industrial sectors such as Biotechnology and renewable energy have been spot lighted as major new growth engines and this competitive situation is getting fiercer. Universities and research institutions in each country selected and announced the future promising technological field which will produce ripple effect in the future on a regular basis. In Korea, various research institutions continue to select and announce the promising technological fields. In this study, we would like to study the method to derive the promising technological field in the field of biotechnology spotlighted as a new growth engine by utilizing patent information. We would like to derive the major technological field by collecting domestic and international patents in the field of biotechnology using IPC code based technological classification and identifying bio technological trends utilizing text mining method for analysis of technological development trends with patents. Patent contour of US and Korea is compared and analyzed through analysis of text mining to derive the general technological development field in the field of biotechnology. After that, we would like to investigate research theme of promising biotechnology focused technological development through details on technological trends through in-depth analysis about technological field which draws interest more and more in Korea and other countries.

• Information Systems Review
• /
• v.21 no.1
• /
• pp.39-59
• /
• 2019

E-learning has improved the educational effect by making it possible to learn anytime and anywhere by escaping the traditional infusion education. As the use of e-learning system increases with the increasing popularity of e-learning, it has become important to measure e-learning satisfaction. In this study, we used the mixed research method to identify satisfaction factors of e-learning. The mixed research method is to perform both qualitative research and quantitative research at the same time. As a quantitative research, we collected reviews in Udemy.com by text mining. Then we classified high and low rated lectures and applied topic modeling technique to derive factors from reviews. Also, this study conducted an in-depth 1:1 interview on e-learning learners as a qualitative research. By combining these results, we were able to derive factors of e-learning satisfaction and dissatisfaction. Based on these factors, we suggested ways to improve e-learning satisfaction. In contrast to the fact that survey-based research was mainly conducted in the past, this study collects actual data by text mining. The academic significance of this study is that the results of the topic modeling are combined with the factor based on the information system success model.