• Information Systems Review
• /
• v.26 no.1
• /
• pp.119-149
• /
• 2024

This study investigates the antecedents and mechanisms influencing trust and behavioral intentions formation towards new AI chatbots, such as ChatGPT, as travel information searching services. Analyzing the roles of variables such as familiarity, novelty, personal innovativeness, information quality and perceived anthropomorphism, the research elucidates the impact of these factors on users' cognitive and affective trust, ultimately affecting their intention to adopt information and sustain the use of the AI chatbot. Results indicate that perceived familiarity and information quality positively influence both cognitive and affective trust, whereas perceived novelty contributes positively only to cognitive trust. Additionally, the personal innovativeness of new AI chatbot users was found to weaken the effect of familiarity on perceived trust, while the perceived level of anthropomorphism of the chatbot amplified the effects of novelty and familiarity on cognitive trust. These findings underscore the importance of considering factors such as familiarity, personal innovativeness, information quality and anthropomorphism in the design and implementation of AI chatbots, affecting trust and behavioral intention.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4270-4284
• /
• 2019

This study presents a reference model (RM) and the architecture of a cognitive health advisor (CHA) that integrates information with ambient intelligence. By controlling the information using the CHA platform, the reference model can provide various ambient intelligent solutions to a user. Herein, a novel approach to a CHA RM based on evolutional cyber-physical systems is proposed. The objective of the CHA RM is to improve personal health by managing data integration from many devices as well as conduct a new feedback cycle, which includes training and consulting to improve quality of life. The RM can provide an overview of the basis for implementing concrete software architectures. The proposed RM provides a standardized clarification for developers and service designers in the design and implementation process. The CHA RM provides a new approach to developing a digital healthcare model that includes integrated systems, subsystems, and components. New features for chatbots and feedback functions set the position of the conversational interface system to improve human health by integrating information, analytics, and decisions and feedback as an advisor on the CHA platform.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.14-17
• /
• 2022

Due to the development of IT technology and the on-going Coronavirus disease, non-face-to-face services have been activated. To overcome the inconvenience of non-face-to-face service, service providers have adopted chatbots as a way to feel like a human being. As the increasing chatbot services, chatbot builders have emerged, which can help non-developers to build them. Although its popularity has increased, its performance evaluation has not been conducted on such chatbot builders. In this paper, we implement a prototype chatbot that classifies hospital departments in the medical field using Dialogflow and Rasa, which are popular chatbot builders. By measuring the accuracy of the chatbot's classification of medical subjects, we evaluated the level of accuracy that the most used chatbot builder can have when they are used to build a chatbot service. The simulation results showed that Dialogflow had 87%, 65%, and 60%, and Rasa did 64%, 70%, and 63% in surgery dermatology, and otolaryngology, respectively.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.44-49
• /
• 2023

이 연구는 MBTI 심리기능을 근거로 사용자 유형을 ST와 NF로 구분하고, 그룹별로 나눈 일상대화를 전사 후 분석하여 대화에서 나타나는 청자의 공감적 반응이 성향에 따라 차별화되는 점을 발견하고 이를 챗봇 대화 실험에 적용하여 분석결과의 유효성을 귀납적으로 증명하였다. 고성능의 초대규모 생성모델을 필두로 한 채팅 에어전트 구현이 보편화된 시점에서 진정 가치있는 대화 모델은 유창한 언어 구사 능력뿐만 아니라 사용자의 성향에 적합한 만족스러운 대화 경험을 제공할 수 있어야 함을 시사한다. 이 연구는 리얼월드의 대화 방식을 모방하여 챗봇 대화로 재현하였다는 점에서 실질적인 B2C 대화 서비스의 질적 향상에 기여도가 높을 것으로 기대된다.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.35-43
• /
• 2023

This paper emphasizes that information received in disaster situations can lead to disparities in the effectiveness of communication, potentially causing damage. As a result, there is a growing demand for disaster and safety information among citizens. A user-centered disaster and safety information application service is designed to address the rapid dissemination of disaster and safety-related information, bridge information gaps, and alleviate anxiety. Through the Open API (Open Application Programming Interface), we can obtain clear information about the weather, air quality, and guidelines for disaster-related actions. Using chatbots, we can provide users with information and support decision-making based on their queries and choices, utilizing cloud APIs, public data portal open APIs, and solution knowledge bases. Additionally, through Mashup techniques with the Google Maps API and Twitter API, we can extract various disaster-related information, such as the time and location of disaster occurrences, update this information in the disaster database, and share it with users.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.182-190
• /
• 2024

Various artificial intelligence neural network models that have emerged since 2014 enable the creation of new content beyond the existing level of information discrimination and withdrawal, and the recent generative artificial intelligences such as ChatGPT and Gall-E2 create and present new information similar to actual data, enabling natural interaction because they create and provide verbal expressions similar to humans, unlike existing chatbots that simply present input content or search results. This study aims to present a model that can improve the ChatGPT communication skills of university students through curriculum research on ChatGPT, which can be participated by students from all departments, including engineering, humanities, society, health, welfare, art, tourism, management, and liberal arts. It is intended to design a way to strengthen competitiveness to embody the practical ability to solve problems through ethical attitudes, AI-related technologies, data management, and composition processes as knowledge necessary to perform tasks in the artificial intelligence era, away from simple use capabilities. It is believed that through creative education methods, it is possible to improve university awareness in companies and to seek industry-academia self-reliant courses.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.126-133
• /
• 2024

Large language models (LLMs) have revolutionized the global landscape of technology beyond natural language processing. Owing to their extensive pre-training on vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without additional fine-tuning. General-purpose chatbots based on LLMs can optimize the efficiency of radiologists in terms of their professional work and research endeavors. Importantly, these LLMs are on a trajectory of rapid evolution, wherein challenges such as "hallucination," high training cost, and efficiency issues are addressed, along with the inclusion of multimodal inputs. In this review, we aim to offer conceptual knowledge and actionable guidance to radiologists interested in utilizing LLMs through a succinct overview of the topic and a summary of radiology-specific aspects, from the beginning to potential future directions.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.37-46
• /
• 2019

The purpose of this study is to explore the effects of the use of artificial intelligence chatbots on improving Korean college students' English grammar skills. 70 undergraduate students participated in the present study. They were taking a General English class offered by a university in Korea. There were two groups in this study. Participants in the chatbot group consisted of 36 students while those in the human group were 34. Over 16 weeks, the chatbot group engaged in ten chat sessions with a chatbot while the human group had a chat with a human chat partner. Both pre- and post-tests were performed to examine changes in the participants' grammar skills over time. To compare the improvement between the two groups, an independent t-test was then run. Main findings are as follows: First, participants in both groups significantly improved their English grammar skills, indicating the beneficial effects of engaging in chat. Also, there was a statistically significant difference in the improvement between the chatbot and human groups, indicating the superior effects of the chatbot use. This study confirmed the improved grammar skills by the participants in the chatbot group, comparison with those in the human group. Based on these findings, suggestions for the future chatbot study are discussed.

• Knowledge Management Research
• /
• v.22 no.1
• /
• pp.287-308
• /
• 2021

This study aims to explore how the effects of the perceived social presence on trust and live chat adoption intention vary with the types of live chats in e-commerce context. As technology develops, live chat with the seller in e-commerce is rapidly replaced by AI-assisted live chat called chat-bot. However, it is not well known how the buyers perceive the difference between the chat with seller and the chat-bot. This study therefore proposes first, the perceived social presence toward the seller will influence trust and the live chat adoption. Second, the effects of social presence will be stronger when using live chat with seller than using chat-bot. To validate, we collect data from 232 e-commerce users and confirm the first proposition. However, the higher level of the social presence effect of live chat with seller is not clearly revealed. This study is expected to provide researchers and managers who are interested in AI-based chatbots with useful theoretical and practical implications.

• Journal of Industrial Convergence
• /
• v.20 no.4
• /
• pp.23-30
• /
• 2022

Recently, with the development of artificial intelligence (AI) and deep learning, the importance of conversational artificial intelligence chatbots is being highlighted. In addition, chatbot research is being conducted in various fields. To build a chatbot, it is developed using an open source platform or a commercial platform for ease of development. These chatbot platforms mainly use RNN and application algorithms. The RNN algorithm has the advantages of fast learning speed, ease of monitoring and verification, and good inference performance. In this paper, a method for improving the inference performance of RNNs and applied algorithms was studied. The proposed method used the word group expansion learning technique of key words for each sentence when RNN and applied algorithm were applied. As a result of this study, the RNN, GRU, and LSTM three algorithms with a cyclic structure achieved a minimum of 0.37% and a maximum of 1.25% inference performance improvement. The research results obtained through this study can accelerate the adoption of artificial intelligence chatbots in related industries. In addition, it can contribute to utilizing various RNN application algorithms. In future research, it will be necessary to study the effect of various activation functions on the performance improvement of artificial neural network algorithms.