• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.87-96
• /
• 2023

ChatGPT, a leader in generative AI, can use natural expressions like humans based on large-scale language models (LLM). The ability to grasp the context of the language and provide more specific answers by algorithms is excellent. It also has high-quality conversation capabilities that have significantly developed from past Chatbot services to the level of human conversation. In addition, it is expected to change the operation method of the tourism industry and improve the service by utilizing ChatGPT, a generative AI in the tourism sector. This study was conducted to explore ChatGPT trends and paradigms in tourism. The results of the study are as follows. First, keywords such as tourism, utilization, creation, technology, service, travel, holding, education, development, news, digital, future, and chatbot were widespread. Second, unlike other keywords, service, education, and Mokpo City data confirmed the results of a high degree of centrality. Third, due to CONCOR analysis, eight keyword clusters highly relevant to ChatGPT in the tourism sector emerged.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.1
• /
• pp.31-42
• /
• 2010

GPM(Generic Product Model) developed by Hitachi in Japan is a common data model to integrate and share life cycle data of nuclear power plants. GPM consists of GPM core model, an abstract model, implementation language for the model and reference library written in the language. GPM core model has a feature that it can construct a semantic network model consisting of relationships among objects. Initial GPM developed and provided GPML as an implementation language to support the feature of the core model, but afterwards the GPML was replaced by GPM-XML based on XML to achieve data interoperability with heterogeneous applications accessing a GPM data model. However, data models written in GPM-XML are insufficient to be used as a semantic network model for lack of studies which support GPM-XML and enable the models to be used as a semantic network model. This paper proposes OWL as the implementation language for GPM core model because OWL can describe ontologies similar to semantic network models and has an abundant supply of technical standards and supporting tools. Also, OWL which can be expressed in terms of RDF/XML based on XML guarantees data interoperability. This paper uses OWL DL, one of three sublanguages of OWL, because it can guarantee complete reasoning and the maximum expressiveness at the same time. The contents of this paper introduce the way how to overcome the difference between GPM and OWL DL, and, base on this way, describe how to convert the reference library written in GPML into ontologies based on OWL DL written in RDF/XML.

• Journal of the Korean earth science society
• /
• v.40 no.3
• /
• pp.283-299
• /
• 2019

The purpose of this study is to identify the conflict frames in the process of designating the national geopark, among local residents, geology experts, and local public officials. For this purpose, the progress of the public hearing on the implementation of the national geopark in Buan and Gochang were recorded with prior consent from the participants and transferred in text form. Subsequently, we developed a reference frames for analyzing conflict frames through literature review, and analyzed the conflict frames by three researchers based on this. These analyzed conflict frames were again analyzed by using semantic network analysis. The results are as follows. In the Buan area, 'Sagree' frame, 'Snot' frame, and 'Sdisagree' frame showed high eigenvector centrality, and 'Gharm' frame and 'Cmeconomy' frame were closely connected to the 'Snot' frame located at the center of the semantic network. In the Gochang area, 'Aresource' frame, 'Cmexample' frame, and 'Gharm' frame showed high eigenvector centrality, and 'Gharm' frame and 'Cmproblemsolution' frame were closely connected to the 'Snot' frame located at the center of the semantic network. Through these results, we could see that there is still the conflict about the certification of national geopark between stakeholders in Buan, and that Gochang's stakeholders are proudly aware of their own resources. The Buan's stakeholders focused on economic gains in resolving conflicts, while Gochang's stakeholders focused on problem solving. This result of this study provides information in conflict from the national geopark in other regions.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.71-80
• /
• 2022

The purpose of this study is to analyze the social perception of invention education center using big data analysis method. For this purpose, data from January 2014 to September 2021 were collected using the Textom website as a keyword searched for 'invention+education+center' in blogs, cafes, and news channels of NAVER and DAUM website. The collected data was refined using the Textom website, and text mining analysis and semantic network analysis were performed by the Textom website, Ucinet 6, and Netdraw programs. The collected data were subjected to a primary and secondary refinement process and 60 keywords were selected based on the word frequency. The selected key words were converted into matrix data and analyzed by semantic network analysis. As a result of text mining analysis, it was confirmed that 'student', 'operation', 'Korea Invention Promotion Association', and 'Korean Intellectual Property Office' were the meaningful keywords. As a result of semantic network analysis, five clusters could be identified: 'educational operation', 'invention contest', 'education process and progress', 'recruitment and support for business', and 'supervision and selection institution'. Through this study, it was possible to confirm various meaningful social perceptions of the general public in relation to invention education center on the internet. The results of this study will be used as basic data that provides meaningful implications for researchers and policy makers studying for invention education.

• Korean Association of Arts Management
• /
• no.50
• /
• pp.5-31
• /
• 2019

The main purpose of this study was to use Deep Learning based Topic Modeling and Semantic Network Analysis to examine research trend of arts management-related papers in korea. For this purpose, research subjects such as 'The Journal of Cultural Policy', 'The Journal of Cultural Economics', 'The Journal of Culture Industry', 'The Journal of Arts Management', and 'The Journal of Human Content', which are the registered journal of the National Research Foundation of Korea directly or indirectly related to arts management field. From 1988 to 2017, a total of 2,110 domestic journals' signature, abstract, and keyword were analyzed. We tried Big Data analysis such as Topic Modeling and Semantic Network Analysis to examine changes in trends in arts management. The analysis program used open software R and standard statistical software SPSS. Based on the results of the analysis, the implications and limitations of the study and suggestions for future research were discussed. And the potential for development of convergent research such as Arts & Artificial Intelligence and Arts & Big Data.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1376-1384
• /
• 2016

Computers require analytic and processing capability for all possibilities of human expression in order to process sentences like human beings. Linguistic information processing thus forms the initial basis. When analyzing a sentence syntactically, it is necessary to divide the sentence into components, find obligatory arguments focusing on predicates, identify the sentence core, and understand semantic relations between the arguments and predicates. In this study, the method applied a case frame dictionary based on The Korean Standard Dictionary of The National Institute of the Korean Language; in addition, we used a CRF Model that constructed subcategorization of predicates as featured in Korean Lexical Semantic Network (UWordMap) for semantic role labeling. Automatically tagged semantic roles based on the CRF model, which established the information of words, predicates, the case-frame dictionary and hypernyms of words as features, were used. This method demonstrated higher performance in comparison with the existing method, with accuracy rate of 83.13% as compared to 81.2%, respectively.

• Journal of Information Management
• /
• v.39 no.4
• /
• pp.121-154
• /
• 2008

In this paper, a ontology-based keyword structuring method is proposed to represent the knowledge structure of scholarly documents and to make inferences from the semantic relationships holding among them. The characteristics of thesaurus as a knowledge organization system(KOS) for subject heading is critically reviewed from the information retrieval point of view. The domain concepts are identified and classified by analysis of the information activities occurring in a general research process based on scholarly sensemaking model. The ontological structure of keyword set is defined in terms of the semantic relationship of the canonical concepts which constitute scholarly documents such as journal articles. As a result, each ontologically structured keyword set of a document represents the knowledge structure of the corresponding document as semantic index. By means of the axioms and inference rules defined for information needs, users can efficiently explore the scholarly communication network built on the semantic relationship among documents in an analytic way based on the scholarly sensemaking model in oder to efficiently retrieve the relevant information for problem solving.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.143-156
• /
• 2023

To precisely and reliably analyze the contents of the satellite imagery, recognizing the clouds which are the obstacle to gathering the useful information is essential. In recent times, deep learning yielded satisfactory results in various tasks, so many studies using deep neural networks have been conducted to improve the performance of cloud detection. However, existing methods for cloud detection have the limitation on increasing the performance due to the adopting the network models for semantic image segmentation without modification. To tackle this problem, we introduced the multi-branch neural architecture search to find optimal network structure for cloud detection. Additionally, the proposed method adopts the soft intersection over union (IoU) as loss function to mitigate the disagreement between the loss function and the evaluation metric and uses the various data augmentation methods. The experiments are conducted using the cloud detection dataset acquired by Arirang-3/3A satellite imagery. The experimental results showed that the proposed network which are searched network architecture using cloud dataset is 4% higher than the existing network model which are searched network structure using urban street scenes with regard to the IoU. Also, the experimental results showed that the soft IoU exhibits the best performance on cloud detection among the various loss functions. When comparing the proposed method with the state-of-the-art (SOTA) models in the field of semantic segmentation, the proposed method showed better performance than the SOTA models with regard to the mean IoU and overall accuracy.

• Journal of Information Technology Services
• /
• v.13 no.2
• /
• pp.173-184
• /
• 2014

As social network services has become one of the most successful web-based business, recommendation in social network sites that assist people to choose various products and services is also widely adopted. Collaborative Filtering is one of the most widely adopted recommendation approaches, but recommendation technique that use explicit or implicit social network information from social networks has become proposed in recent research works. In this paper, we reviewed and compared research works about recommendation using social network analysis and collaborative filtering in social network sites. As the results of the analysis, we suggested the trends and implications for future research of recommendation in SNSs. It is expected that graph-based analysis on the semantic social network and systematic comparative analysis on the performances of social filtering and collaborative filtering are required.

• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.1111-1119
• /
• 2003

The research of science and engineering needs the latest information from internet resources. But it is a complex and repeated procedure to search and filter web documents from the huge Internet resources. In this paper, we propose the PREA system, which can organize the research paper databases and search World Wide Web documents that the user is interested in. It observes the usage of the local Paper databases and presented web documents and then constructs a profile intelligently. However, to make a profile, we used the modified spreading activation network(MSAN) so that the PREA can search and filter web documents by semantic meaning of user's interest in realtime. The system constructed in multi-agents manner that can cooperate together effectively. The results show the effectiveness of our system to search web documents compared with a commercial search engine.