• Journal of Information Technology Services
• /
• v.23 no.1
• /
• pp.81-95
• /
• 2024

ChatGPT, a generative artificial intelligence(AI) technology that analyzes conversations to identify users' intentions and generates responses in consideration of the context of the conversation, is attracting attention from a user interface (UI) perspective that it can provide information through natural conversations with users. This study examined the effect of functional and playful values experienced by early users of ChatGPT on reuse intention and verified the structural relationship between technological efficacy, experiential values, and reuse intention. To verify the research model and hypotheses, a survey was conducted on college students who used ChatGPT for the first time. A total of 156 responses were received and 154 responses were used for analysis. As a result, both the functional experiential value and playful experiential value in the initial use process had significant effects on the intention to use ChatGPT. In addition, it was found that technological efficiency had a significant effect on functional and playful experiential values.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.570-573
• /
• 2024

본 연구는 대형 언어 모델 (LLM) 시대에 공감적 대화 생성을 위한 감정 인식의 필요성을 확인하고 소형 언어 모델 (SLM)을 통한 미세 조정 학습이 고비용 LLM, 특히 ChatGPT의 대안이 될 수 있는지를 탐구한다. 이를 위해 KoBERT 미세 조정 모델과 ChatGPT를 사용하여 사용자 감정을 인식하고, Polyglot-Ko 미세 조정 모델 및 ChatGPT를 활용하여 공감적 응답을 생성하는 비교 실험을 진행하였다. 실험 결과, KoBERT 기반의 감정 분류기는 ChatGPT의 zero-shot 접근 방식보다 뛰어난 성능을 보였으며, 정확한 감정 분류가 공감적 대화의 질을 개선하는 데 기여함을 확인하였다. 이는 공감적 대화 생성을 위해 감정 인식이 여전히 필요하며, SLM의 미세 조정이 고비용 LLM의 실용적 대체 수단이 될 수 있음을 시사한다.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.2
• /
• pp.89-112
• /
• 2024

Metadata is a crucial component of record management, playing a vital role in properly managing and understanding the record. In cases where automatic metadata assignment is not feasible, manual input by records professionals becomes necessary. This study aims to alleviate the challenges associated with manual entry by proposing a method that harnesses ChatGPT technology for extracting records management metadata elements. To employ ChatGPT technology, a Python program utilizing the LangChain library was developed. This program was designed to analyze PDF documents and extract metadata from records through questions, both with a locally installed instance of ChatGPT and the ChatGPT online service. Multiple PDF documents were subjected to this process to test the effectiveness of metadata extraction. The results revealed that while using LangChain with ChatGPT-3.5 turbo provided a secure environment, it exhibited some limitations in accurately retrieving metadata elements. Conversely, the ChatGPT-4 online service yielded relatively accurate results despite being unable to handle sensitive documents for security reasons. This exploration underscores the potential of utilizing ChatGPT technology to extract metadata in records management. With advancements in ChatGPT-related technologies, safer and more accurate results are expected to be achieved. Leveraging these advantages can significantly enhance the efficiency and productivity of tasks associated with managing records and metadata in archives.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.134-140
• /
• 2018

A chat system is a computer program that understands user's miscellaneous utterances and generates appropriate responses. Sometimes a chat system needs to answer users' simple information-seeking questions. However, previous generative chat systems do not consider how to embed knowledge entities (i.e., subjects and objects in triple knowledge), essential elements for question-answering. The previous chat models have a disadvantage that they generate same responses although knowledge entities in users' utterances are changed. To alleviate this problem, we propose a knowledge entity embedding method for improving question-answering accuracies of a generative chat system. The proposed method uses a Siamese recurrent neural network for embedding knowledge entities and their synonyms. For experiments, we implemented a sequence-to-sequence model in which subjects and predicates are encoded and objects are decoded. The proposed embedding method showed 12.48% higher accuracies than the conventional embedding method based on a convolutional neural network.

• The Journal of Information Systems
• /
• v.25 no.3
• /
• pp.61-90
• /
• 2016

Purpose Recently the usage of Mobile Instant Messenger(MIM) has been increased all over the world. With the development of Mobile Internet, a large amount of mobile application came into being, such as WeChat, the most popular MIM now in China. It has a huge number of registered users, but just only half of them are the "active users". This study intends to examine what factors affect MIM user's continuance intention and actual usage behavior. Design/Methodology/Approach Based on the framework of Perception/Emotion-Behavior and the extended ECM-ISC (Expectation Confirmation Model of IS Continuance), this research introduced some unique variables to a user satisfaction model focusing on perceived/emotional factors in WeChat. In this model, perceived/emotional factors have been divided into enabler factors and inhibitor factors to analyze the effect on continuance intention and actual usage behavior. Also, the moderate effect of the habits was discussed. An online questionnaire survey of 203 WeChat users was conducted and the empirical validation was employed to test the research model. Findings From the empirical results, perceived usefulness, expectation confirmation, and needs for affiliation significantly affected satisfaction. Also, satisfaction influenced continuance intention which led to actual usage behavior. We found that the habit moderates the relationship between satisfaction and continuance intention. The result of this study provides guidance to the developers and operators of WeChat on how to improve enhance users' satisfaction and loyalty.

• Journal of Korean Biological Nursing Science
• /
• v.25 no.3
• /
• pp.183-204
• /
• 2023

Purpose: The purpose of this study was to evaluate the applicability of ChatGPT in biological nursing science education. Methods: This study was conducted by entering questions about the field of biological nursing science into ChatGPT versions GPT-3.5 and GPT-4 and evaluating the answers. Three questions each related to microbiology and pharmacology were entered, and the generated content was analyzed to determine its applicability to the field of biological nursing science. The questions were of a level that could be presented to nursing students as written test questions. Results: The answers generated in English had 100.0% accuracy in both GPT-3.5 and GPT-4. For the sentences generated in Korean, the accuracy rate of GPT-3.5 was 62.7%, and that of GPT-4 was 100.0%. The total number of Korean sentences in GPT-3.5 was 51, while the total number of Korean sentences in GPT-4 was 68. Likewise, the total number of English sentences in GPT-3.5 was 70, while the total number of English sentences in GPT-4 was 75. This showed that even for the same Korean or English question, GPT-4 tended to be more detailed than GPT-3.5. Conclusion: This study confirmed the advantages of ChatGPT as a tool to improve understanding of various complex concepts in the field of biological nursing science. However, as the answers were based on data collected up to 2021, a guideline reflecting the most up-to-date information is needed. Further research is needed to develop a reliable and valid scale to evaluate ChatGPT's responses.

• Asia pacific journal of information systems
• /
• v.33 no.4
• /
• pp.1058-1092
• /
• 2023

This study investigates the perception and adoption of ChatGPT (a large language model (LLM)-based chatbot created by OpenAI) among Korean users and assesses its potential as the next disruptive innovation. Drawing on previous literature, the study proposes perceived intelligence and perceived anthropomorphism as key differentiating factors of ChatGPT from earlier AI-based chatbots. Four individual motives (i.e., perceived usefulness, ease of use, enjoyment, and trust) and two societal motives (social influence and AI anxiety) were identified as antecedents of ChatGPT acceptance. A survey was conducted within two Korean online communities related to artificial intelligence, the findings of which confirm that ChatGPT is being used for both utilitarian and hedonic purposes, and that perceived usefulness and enjoyment positively impact the behavioral intention to adopt the chatbot. However, unlike prior expectations, perceived ease-of-use was not shown to exert significant influence on behavioral intention. Moreover, trust was not found to be a significant influencer to behavioral intention, and while social influence played a substantial role in adoption intention and perceived usefulness, AI anxiety did not show a significant effect. The study confirmed that perceived intelligence and perceived anthropomorphism are constructs that influence the individual factors that influence behavioral intention to adopt and highlights the need for future research to deconstruct and explore the factors that make ChatGPT "enjoyable" and "easy to use" and to better understand its potential as a disruptive technology. Service developers and LLM providers are advised to design user-centric applications, focus on user-friendliness, acknowledge that building trust takes time, and recognize the role of social influence in adoption.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.287-308
• /
• 2023

After launching its service in November 2022, ChatGPT has rapidly increased the number of users and is having a significant impact on all aspects of society, bringing a major turning point in the history of artificial intelligence. In particular, the inference ability of large language models such as ChatGPT is improving at a rapid pace through prompt engineering techniques. This reasoning ability can be considered as an important factor for companies that want to adopt artificial intelligence into their workflows or for individuals looking to utilize it. In this paper, we begin with an understanding of in-context learning that enables inference in large language models, explain the concept of prompt engineering, inference with in-context learning, and benchmark data. Moreover, we investigate the prompt engineering techniques that have rapidly improved the inference performance of large language models, and the relationship between the techniques.

• 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.

• Information Systems Review
• /
• v.25 no.2
• /
• pp.125-144
• /
• 2023

Generative Artificial Intelligence (AI) technology is gaining global attention as it can automatically generate sentences, images, and voices that humans previously generated. In particular, ChatGPT, a representative generative AI service, shows proactivity and accuracy differentiated from existing chatbot services, and the number of users is rapidly increasing in a short period of time. Despite this growing interest in generative AI services, most preceding studies are still in their infancy. Therefore, this study utilized LDA topic modeling and keyword network diagrams to derive success factors for generative AI services and to propose successful business strategies based on them. In addition, using ChatGPT, a new research methodology that complements the existing text-mining method, was presented. This study overcomes the limitations of previous research that relied on qualitative methods and makes academic and practical contributions to the future development of generative AI services.