• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.467-472
• /
• 2021

본 연구는 패션앱 후기글에 나타나는 구매자의 의견에 대한 '평가분석(Evaluation Analysis: EA)'을 수행하여, 이를 기반으로 상품의 검색 및 추천을 수행하는 의류 검색추천 챗봇을 개발하는 LICO 프로젝트의 언어데이터 구축의 일환으로 수행되었다. '평가분석 트리플(EAT)'과 '평가기반요청 쿼드러플(EARQ)'의 구성요소들에 대한 주석작업은, 도메인 특화된 단일형 핵심어휘와 다단어(MWE) 핵심패턴들을 FST 방식으로 구조화하는 DECO-LGG 언어자원에 기반하여 반자동 언어데이터 증강(SSP) 방식을 통해 진행되었다. 이 과정을 통해 20여만 건의 후기글 문서(230만 어절)로 구성된 EVAD 평가주석데이터셋이 생성되었다. 여성의류 도메인의 평가분석을 위한 '평가속성(ASPECT)' 성분으로 14가지 유형이 분류되었고, 각 '평가속성'에 연동된 '평가내용(VALUE)' 쌍으로 전체 35가지의 {ASPECT-VALUE} 카테고리가 분류되었다. 본 연구에서 구축된 EVAD 평가주석 데이터의 성능을 평가한 결과, F1-Score 0.91의 성능 평가를 획득하였으며, 이를 통해 향후 다른 도메인으로의 확장된 적용 가능성이 유효함을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.376-378
• /
• 2022

Artificial intelligence technology is widely used in various fields such as artificial intelligence speakers, artificial intelligence chatbots, and autonomous vehicles. Among these AI application fields, the image processing field shows various uses such as detecting objects or recognizing objects using artificial intelligence. In this paper, data synthesized by a virtual human is used as a method to analyze images taken in a specific space.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.179-184
• /
• 2023

본 연구는 우울감을 느끼거나 대화 상대 부재로 어려움을 겪는 사용자와 정서 교감형 시스템간의 대화로 구성된 한국어 데이터 셋을 구축하고 이때 시스템이 사용할 수 있는 효과적인 응대 전략을 제안하는데 목적이 있다. 데이터셋은 사용자와 시스템 간의 대화 쌍을 기본 단위로 하며, 사용자의 7가지 기본 감정(행복, 슬픔, 공포, 놀람, 분노, 혐오, 중립)과 시스템의 4가지 응대 전략(명료화, 공감적 응대, 제안, 페르소나)에 따라 주석이 된다. 이 중, 공감적 응대 전략은 10가지 독특한 반응 유형(수용적 경청, 후행 발화 요청, 승인/동의, 비승인/재고 요청, 놀람, 격려, 느낌 표시, 상대 발화 반복, 인사, 의견 제시) 및 4가지 후행 발화 요청 유형(무엇, 왜, 어떻게, 그밖에)을 포함하는 구조로 구체화되었다. 이러한 주석은 시스템이 사용자의 다양한 감정을 식별하고 적절한 공감 수준을 나타내는 응답을 생성하는 데 있어 연구적인 의의가 있으며, 필요시 사용자가 부정적 감정을 극복할 수 있는 활동을 제안하는 데 도움을 줄 수 있다는 점에서 실제적인 의의가 있다.

• Asia pacific journal of information systems
• /
• v.34 no.1
• /
• pp.351-371
• /
• 2024

This study aims to assess the impact of chatbot usability and demographics on continuous intention to use across different sectors. The research employed Braun's Bot Usability Scale (BUS11) to measure chatbot usability, focusing on accessibility, quality, conversation quality, privacy risk, and response time. A total of 187 participants completed a survey as part of this study. Variance-based SEM was utilized to examine relationships and test hypotheses. This study contributes to the ongoing discourse on chatbot adoption and user behaviour. It enhances the understanding of chatbot usability, highlighting the role of age in continued intention to use chatbots. The findings suggest that different age groups may possess specific preferences and expectations regarding chatbot usability. These differing preferences can influence their intention to continue using this technology. The study reveals that chatbot usability significantly impacts continuous intention to use and that age moderates the relationship between perceived conversation quality, information, privacy, security, and continuous intention to use. Based on the study's results, it is recommended that chatbot designers enhance usability to promote long-term adoption and usage.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.870-878
• /
• 2019

In this paper, we propose an Attention-based BLSTM for predicting the video compression standard of a video. Recently, in NLP, many researches have been studied to predict the next word of sentences, classify and translate sentences by their semantics using the structure of RNN, and they were commercialized as chatbots, AI speakers and translator applications, etc. LSTM is designed to solve the gradient vanishing problem in RNN, and is used in NLP. The proposed algorithm makes video compression standard prediction possible by applying BLSTM and Attention algorithm which focuses on the most important word in a sentence to a bitstream of a video, not an sentence of a natural language.

• Science of Emotion and Sensibility
• /
• v.21 no.4
• /
• pp.11-24
• /
• 2018

This study was based on previous ones that demonstrate how social exclusion leads to a desire for physical warmth. Research was conducted using odor-induced emotions to predict social exclusion, leading to a pursuit of emotional warmth and avoidance of emotional distance. For this purpose, a preliminary study sought to select odors perceived to be emotionally warm and emotionally distant, after which two experiments verified differences in odor preference between the social exclusion group and the control group. Results indicated that individuals who have experienced social exclusion had a stronger preference for warm odors and a weaker preference for cold odors compared to those who have not been socially ostracized. This study has theoretical value in terms of expanding the social exclusion-induced desire for physical warmth into the emotional dimension as well as examining the avoidance of emotional coldness, which had been overlooked in previous research studies. This also leads to practical implications for comfort foods, character emotions, emotional-space design, and emotions for artificial-intelligence chatbots.

• Journal of the HCI Society of Korea
• /
• v.14 no.1
• /
• pp.35-43
• /
• 2019

This study examines how interactivity and usage mode of a chatbot interface affects user experience. Chatbot has rapidly been commercialized in accordance with improvements in artificial intelligence and natural language processing. However, most of the researches have focused on the technical aspect to improve the performance of chatbots, and it is necessary to study user experience on a chatbot interface. In this article, we investigated how 'interactivity' of an interface and the 'usage mode' referring to situations of a user affect the satisfaction, flow, and perceived usefulness of a chatbot for exploring user experience. As the result, first, the higher level of interactivity, the higher user experience. Second, usage mode showed interaction effect with interactivity on flow, although it didn't show the main effect. In specific, when interactivity is high in usage mode, flow was the highest rather than other conditions. Thus, for designing better chatbot interfaces, it should be considered to increase the degree of interactivity, and for users to achieve a goal easily through various functions with high interactivity.

• Journal of the HCI Society of Korea
• /
• v.14 no.2
• /
• pp.61-69
• /
• 2019

Recently, as a new ICT trend, emerging chatbots are actively introduced in the field of finance. Chatbot conducts services through the interaction of communication with users. The purpose of this study is to investigate the effect of interaction dialogue type on the efficiency, usability, sensibility and perceived security of financial service chatbot. Based on theoretical considerations, I have divided into closed conversation, open conversation, and mixed conversation type based on the conversation style based on the implementation method of chatbot. Three types of Financial Chatbot prototypes were made and the experiments were conducted after account inquiry, account transfer, Q & A financial task execution. As a result of experimental research analysis, chatbot's interaction dialogue type was found to affect efficiency and usability. Users have shown that the interaction of closed conversations and mixed conversations is an intuitive interface that allows financial services to be easily manipulated without error. This study will be used as a resource to improve the user experience that requires deep understanding of financial chatbot users who should consider both the emotional element of artificial intelligence that provides services through natural conversation and the functional elements that perform financial business can be.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.4
• /
• pp.440-448
• /
• 2019

In this paper, we propose an ordering chatbot that can process multiple keywords based on recursive slot-filling method. In general, in case of an order service using chatbots, the whole order process is performed only according to the sequence defined by the developer. That is, among all the information needed for the whole order process, only one input can be processed at one time. In order to reduce processing step for the order, we propose a recursive slot-filling method which fills out multiple slots per one time by extracting multiple keywords. First, a keyword array for the order is created according to the order related information. Next, from the input sentence of a user, multiple keywords is extracted. Corresponding slots for a keyword array will be filled with the extracted keywords. Finally, recursive routine will be executed to fill out all the blank in the keyword array. The usability and validity of the proposed method will be shown from the implementation of a smartphone application.