• The Journal of the Korea Contents Association
• /
• v.22 no.7
• /
• pp.136-148
• /
• 2022

This study aims to examine the effects of customer experience on the relationship between brand trust and customer experience. The survey was conducted on consumers who experienced chatbot service through internet shopping mall, and the research hypothesis was verified by analyzing the final 299 questionnaires. The results of the study showed that the customer experience using chatbot service had a positive effect on chatbot trust, had a positive effect on shopping mall trust, seller trust and brand trust through the mediating role of chatbot trust, and the social presence of chatbot had a moderating effect in the trust transfer. This study provides a theoretical basis that customer experience of chatbot service has positive effect on brand trust through chatbot trust, and suggests implications in that chatbot service can be an important means of marketing. In future studies, various studies related to chatbot trust are needed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.233-234
• /
• 2021

본 논문에서는 Microsoft Bot Framework와 Microsoft Azure Service, LUIS AI를 활용하여 쇼핑몰 이용에 도움을 주는 쇼핑 챗봇을 설계하고 구현한다. 이 챗봇은 쇼핑몰을 이용하는 사용자들에게 대화형 인터페이스를 통한 편의성을 제공하고 접근성을 증가시킨다. 또한 직접 찾는 방식이 아닌 AI의 선택이 중심이 되어 검색 시간 감소로 인한 시간 절약 효과를 얻을 수 있다.

• Knowledge Management Research
• /
• v.21 no.4
• /
• pp.211-225
• /
• 2020

We investigate factors affecting chatbot use intention of online shopping mall users. We identify theoretical foundations from the literature and postulate that accuracy, personalization level, intelligence, intimacy, social presence, and piracy concern should affect intention to use more or negative intention to use. Based on 300 responses from online shopping mall chatbot users in Korea, we run the statistical analysis to assure the reliability and validity of the measurements. From the multiple regression analysis, we find that personalization level, intelligence, social presence, and privacy concerns significantly affect intention to use more. In contrast, we find that accuracy and privacy concerns significantly affect negative intention to use. This work will present pragmatic implications upon the design and management of chatbot in order to not only incent customers to use more but reduce factors that may cause negative use intention. Among functional factors, personalization and intelligence increases the intention to use more while accuracy decreases negative intention to use. Among emotional factors such as intimacy and social presence, we find that only social presence significantly increases intention to use more. Privacy concerns is found to decrease intention to use and increase negative intention to use.

• Journal of the HCI Society of Korea
• /
• v.14 no.2
• /
• pp.71-81
• /
• 2019

As AI technology develops, its application has been extended to diverse fields. In particular, AI-enabled Chatbot services have garnered growing attention and such services are more important as a tool of communication in mobile shopping. However, research on chatbots is in its early stage and the understanding of chatbots in the context of mobile commerce is very limited. The purpose of this study is to empirically investigate consumer responses to a shopping chatbot with a focus on the effects of chatbot agent types and message types. Specifically, a $2{\times}2$ between-subjects experimental design, with the agent type (secretary/friend) and the message type (factual/evaluative) as the independent variables, was employed. The results show that although main effects of chatbot agent and message types are not found, interaction effects between chatbot agents and message types on consumer responses are significant. Specifically, when the agent type was a secretary, consumer responses to product recommendation with a factual message were more positive. On the other hand, in the case of the friend agent, the evaluative message led to more positive responses. The findings suggest that communication elements are important in the understanding of consumer responses to chatbots in mobile shopping and effective strategies for utilizing chatbots for mobile commerce should be considered.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.185-186
• /
• 2020

최근 제품을 주문하거나 상품을 조회하는 등의 간단한 상담을 챗봇을 이용하여 자동화하는 온라인 쇼핑몰들이 늘어나고 있다. 이는 고객을 상담하는 상담원의 업무를 줄여줄 뿐 아니라 고객 상담을 즉각적이고 효율적으로 진행할 수 있다. 또한 사용자의 입장에서 챗봇은 처음 이용하는 사람도 사용하기가 쉽고, 상담원과의 연결까지 기다리지 않고 사용자가 원하는 시간에 커뮤니케이션이 가능하고, 기업 측면에서는 인건비가 감소되고 고객관리가 용이해진다는 장점이 있다. 그러나 챗봇은 주어진 질문에만 대답할 수 있고, 처음 메뉴를 파악하기 힘들다는 단점이 있다. 따라서 본 논문에서는 카카오톡 오픈빌더를 사용하여 질문의도를 파악하는 intent와 entity를 추출한 뒤 딥러닝을 통해 체계적으로 학습을 진행한다. 이를 통해 주어지지 않은 질문들을 파악한다. 또한, 오픈빌더의 시나리오 선택 기능을 활용하여 초기에 선택할 수 있는 메뉴를 파악하기 쉽도록 구현하였다. 사용자는 본 논문에서 제안하는 챗봇을 통해 사용자는 상담에 필요한 도움을 받을 수 있을 것으로 기대된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.474-477
• /
• 2017

최근 모바일 메신저 챗봇 API를 이용한 서비스 시장이 활성화되고 있다. 챗봇은 대화형 인터페이스 상에서 규칙 또는 AI로 유저와의 인터랙션을 하는 서비스로 지도, 쇼핑, 금융 등의 앱들이 챗봇 안으로 흡수되어 앱이나 웹에 별도로 접속하지 않아도 된다는 이점이 있다. 챗봇에 필요한 자동응답 API는 대표적으로 텔레그램, 페이스북 메신저, 네이버 톡톡, 카카오톡과 같은 메신저 앱에서 구현 가능하다. 아직까지 카카오톡 메신저는 챗봇 구현 환경이 제한적이라는 단점이 있지만, 국내 메신저 사용시간 점유율 94%를 차지하여 유저 접근성이 뛰어나다. 따라서 이 서비스의 타겟층이 주부 및 1인 가구이므로 서비스 범위보다는 접근성을 기준으로 두고 메신저 앱을 카카오톡으로 선택했다. 본 논문은 카카오톡 자동응답 API를 이용한 대화형 서비스를 연구 및 개발하는데 중점을 두고 있다. 이 대화형 서비스는 요리에 관한 전반적인 정보를 제공하며, 서비스 이용자에게 간편한 요리환경을 제공할 수 있도록 한다. 다양한 세부 기능을 확장한다면 효율적인 대화형 서비스가 될 것으로 사료된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.570-573
• /
• 2019

스마트폰의 대중화로 인터넷 이용률이 증가함에 따라 온라인 쇼핑 시장의 규모가 커지는 반면 대부분의 온라인 쇼핑몰은 시각장애인의 접근성이 미흡하여 온라인 쇼핑의 어려움을 겪고 있다. 그 불편함은 '정보화 사회에서의 소외감' 이라는 정신적 피해로 이어지고 있는 심각한 상황이다. 따라서 이 불편함을 해소하고 정보 접근의 격차를 줄이고자 <쇼움이>를 설계, 구현하게 되었다. <쇼움이>는 챗봇을 활용하여 일문일답으로 입력 받아 시각장애인들이 쉽고 편리하게 상품을 검색/파악할 수 있도록 설계, 구현되었으며, 시각장애인들이 파악하지 못했던 이미지 내의 상품 정보를 분석하여 텍스트와 음성으로 안내한다. 또 관심 상품 등록, 상품 링크 공유 기능을 구현하였다. 또한 사용자의 편리성 확보를 위해 버튼을 포함한 모든 항목이 안드로이드의 voice-assistant 로 읽히도록 설계, 구현하였다.

• Journal of Fashion Business
• /
• v.25 no.4
• /
• pp.79-91
• /
• 2021

Currently, chatbot, a conversational platform based on artificial intelligence, is drawing attention as a new marketing channel. This study attempted to verify the effect of the anthropomorphism, message type, and media self-efficacy level on purchase intention. The experimental design of this study was a 2 (anthropomorphism level of shopping chatbot: low vs. high) × 2 (message type: factual vs. evaluative) × 2 (media self-efficacy: low vs. high) three-way mixed analysis of variance (ANOVA). This study conducted a survey by the convenience sampling method of 402 women in their 20s and 30s living in Seoul and the Gyeonggi area who were aware of chatbot services. For the final analysis, 388 questionnaires were used. Data were analyzed with the SPSS 23 program and three-way ANOVA. Simple main effects analysis was conducted. The results of this study were as follows. First, there were statistically significant differences in purchase intention according to anthropomorphism level, message type, and media self-efficacy. Second, message type and media self-efficacy showed statistically significant interaction effects on purchase intention. Lastly, anthropomorphism and the media self-efficacy level and the message type of the shopping chatbots showed significant three-way interaction effects on purchase intention.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.4
• /
• pp.573-593
• /
• 2020

This study analyzes consumers' responses toward chatbot services in a fashion retail context. Anthropomorphism and personalization of chatbots are proposed as critical features of a chatbot service that attract positive behavioral intentions from consumers. Social presence, trust, and enjoyment are expected to mediate associations among chatbot characteristics and consumers' acceptance of the service. The experiment was conducted in a controlled laboratory; participants were instructed to engage with a virtual shopping chatbot service via their cell phone and complete a questionnaire online. A total of 189 participants participated in this study along with and four experimental groups of 2 (anthropomorphism: high / low) × 2 (personalization: high / low) were formed with between-subject design. The collected data were analyzed using SPSS 25.0 and SPSS PROCESS Macro programs. The results show that the effect of anthropomorphism and personalization of chatbots on consumers' service acceptance intention when using fashion shopping chatbot service were mediated sequentially by social presence, trust, social presence and enjoyment. This study provides meaningful evidence on the effects of chatbots characterized by anthropomorphism and personalization on consumer responses, acceptance intention and associated psychological mechanisms by expanding the field of consumer behavior into chatbot services.

• Fashion & Textile Research Journal
• /
• v.24 no.2
• /
• pp.183-194
• /
• 2022

This study aims to understand the consumers' negative responses to communication failure of chatbots caused by their imperfections. Specifically, this study examines 1) the relationship among chatbot's communication failure, dissatisfaction, negative behavior (complaint, negative word-of-mouth (nWOM), and inertia); 2) the moderating effect of technostress on the relationship between chatbot's communication failure and dissatisfaction; 3) the differences in the negative responses between the generation MZ and the previous generations. Data were collected via an online survey. First, the participants interacted with the chatbot developed for this survey, to experience the chatbot's communication failure. Thereafter, they responded to a questionnaire. PLS-SEM was conducted using the R software environment to test the hypotheses. This study empirically identified that chatbot's communication failure positively affected dissatisfaction. In addition, the customers who were more dissatisfied with the chatbot's communication failures were more likely to complain than engage in nWOM. Compared to the generation MZ, chatbot's communication failure caused a higher level of dissatisfaction in previous generations. The results suggest that online shopping malls should carefully introduce an improved chatbot service after minimizing its communication failure rate. The chatbot developers of online shopping malls targeting middle-aged and elderly consumers should strive to develop and implement strategies to further alleviate consumers' dissatisfaction in the situation of chatbot's communication failure.