• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.335-336
• /
• 2022

본 논문에서는 시간대와 대화 주제를 활용하여 카테고리별로 적절한 SNS 광고 시간대 예측 방법을 제시한다. 위의 분석으로 광고주들에게 적절한 광고시간을 제안할 수 있다. 연관규칙분석 알고리즘인 apriori를 사용하였다. 주제는 상거래(쇼핑), 미용과 건강, 시사/교육, 식음료, 여가생활로 추려서 분석하였다. 연관분석 결과, 미용과 건강이 18시, 17시, 16시에 가장 활발히 대화를 나누었다. 상거래(쇼핑)이 14시, 16시, 17시 순으로 가장 활발히 대화를 나누었으며, 시사/교육이 15시, 17시, 16시 순으로 많은 대화를 나누었으며, 식음료가 18시, 17시, 19시 순으로 대화를 많이 나눈 것을 확인했다. 마지막으로, 여가생활은 22시, 23시, 21시 순으로 각각의 대화 주제별로 가장 많이 대화를 나눈 시간대가 달라지는 것을 확인할 수 있었다. 이를 통해 소비자 입장에서는 알맞은 광고를 적절한 시간대에 추천받을 수 있다.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.368-369
• /
• 2023

대화 데이터 기반 광고 추천은 광고 마케팅에서 고객 맞춤형 광고 제공, 마케팅 효과 극대화 등을 위한 중요한 기술로 주목받고 있다. 본 논문에서는 모바일 인스턴스 메신저인 카카오톡 대화창에서 발생한 텍스트 데이터를 기반으로 대화 내용을 분석하여 대화 주제별 적절한 광고 키워드를 제안한다. 이를 위해 주제별 대화 내용을 미용, 식음료, 상거래로 세분하고 KoNLPy 의 Okt 를 이용하여 텍스트 전처리를 수행하고 키워드별로 빈도수를 뽑아 워드 클라우드를 제시한다. 또한, 잠재 디리클레 할당(Latent Dirichlet Allocation, LDA)을 기반으로 대화 주제를 세분화한 뒤 라벨링을 통해 주제별 대화 키워드를 분석한다. 실험 결과, 대화 주제를 온라인 쇼핑, 헤어, 뷰티 관리, 음식으로 나눌 수 있었으며, 토픽별 상위 키워드를 Word2Vec 을 통해 특정 단어와 유사한 키워드를 도출하여 적절한 광고 키워드를 제시할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.253-257
• /
• 2023

최근 다양한 대화 시스템이 스마트폰 어시스턴트, 자동 차 내비게이션, 음성 제어 스피커, 인간 중심 로봇 등의 실세계 인간-기계 인터페이스에 적용되고 있다. 하지만 대부분의 대화 시스템은 텍스트 기반으로 작동해 다중 모달리티 입력을 처리할 수 없다. 이 문제를 해결하기 위해서는 비디오와 같은 다중 모달리티 장면 인식을 통합한 대화 시스템이 필요하다. 기존의 비디오 기반 대화 시스템은 주로 시각, 이미지, 오디오 등의 다양한 자질을 합성하거나 사전 학습을 통해 이미지와 텍스트를 잘 정렬하는 데에만 집중하여 중요한 행동 단서와 소리 단서를 놓치고 있다는 한계가 존재한다. 본 논문은 이미지-텍스트 정렬의 사전학습 임베딩과 행동 단서, 소리 단서를 활용해 비디오 기반 대화 시스템을 개선한다. 제안한 모델은 텍스트와 이미지, 그리고 오디오 임베딩을 인코딩하고, 이를 바탕으로 관련 프레임과 행동 단서를 추출하여 발화를 생성하는 과정을 거친다. AVSD 데이터셋에서의 실험 결과, 제안한 모델이 기존의 모델보다 높은 성능을 보였으며, 대표적인 이미지-텍스트 자질들을 비디오 기반 대화시스템에서 비교 분석하였다.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.85-110
• /
• 2018

A chatbot is an interactive assistant that utilizes many communication modes: voice, images, video, or text. It is an artificial intelligence-based application that responds to users' needs or solves problems during user-friendly conversation. However, the current version of the chatbot is focused on understanding and performing tasks requested by the user; its ability to generate personalized conversation suitable for relationship-building is limited. Recognizing the need to build a relationship and making suitable conversation is more important for social chatbots who require social skills similar to those of problem-solving chatbots like the intelligent personal assistant. The purpose of this study is to propose a text analysis method that evaluates relationships between chatbots and users based on content input by the user and adapted to the communication situation, enabling the chatbot to conduct suitable conversations. To evaluate the performance of this method, we examined learning and verified the results using actual SNS conversation records. The results of the analysis will aid in implementation of the social chatbot, as this method yields excellent results even when the private profile information of the user is excluded for privacy reasons.

• 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 the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.620-631
• /
• 2021

The study aim to test the effect of voice agent's preceding utterance type on the user experience in the smart home contexts by conversation types. Based on two types of conversation (task-oriented vs. relationship-oriented conversations) and two types of utterance (preceding vs. response utterances), four different scenarios were designed for experimental study. A total of 62 participants were divided into two groups by utterance type, and exposed to two scenarios of the conversation types. Likeability, psychological reactance, and perceived intelligence were measured for the user experience of conversational agent. The result showed main effects of likeability in task-oriented conversations, and of psychological reactance in preceding utterances. The interaction effect demonstrated that preceding conversation improved the likeabilitty and perceived intelligence in the task-oriented conversations.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.27-38
• /
• 2023

In this paper, we propose a conversational AI agent based on continual learning that can continuously learn and grow with new data over time. A continual learning-based conversational AI agent consists of three main components: Task manager, User attribute extraction, and Auto-growing knowledge graph. When a task manager finds new data during a conversation with a user, it creates a new task with previously learned knowledge. The user attribute extraction model extracts the user's characteristics from the new task, and the auto-growing knowledge graph continuously learns the new external knowledge. Unlike the existing conversational AI agents that learned based on a limited dataset, our proposed method enables conversations based on continuous user attribute learning and knowledge learning. A conversational AI agent with continual learning technology can respond personally as conversations with users accumulate. And it can respond to new knowledge continuously. This paper validate the possibility of our proposed method through experiments on performance changes in dialogue generation models over time.

• Science of Emotion and Sensibility
• /
• v.26 no.3
• /
• pp.115-128
• /
• 2023

This study examines the effects of a new app-based intervention program for conversational skills of children with high-functioning autism spectrum disorder (ASD). Participants in this study comprised 26 children diagnosed with autism, Asperger's syndrome, or pervasive developmental disorder-not otherwise specified (PDD-NOS). Participants were randomly assigned into a treatment group or a control group according to their ages, IQ, SCQ, and ASSQ scores. The treatment group met with teachers once a week for a single non-face-to-face class for nine weeks, along with conversation training at home using an app. The control group did not participate in any specific programs for conversational skills. Conversation data of all participants were collected before and after the intervention to compare the two groups based on changes in the conversational turn-taking and topic manipulation skills. When analyzed with respect to a Group X Period analysis of variance (ANOVA), the data indicated maintenance on the rate of appropriate listener's verbal responses in the treatment group, whereas the rate of inappropriate listener's verbal response significantly declined in the control group. In addition, the rate of conversation initiation and maintenance and the rate of appropriate initiation improved in the treatment group, whereas the rate of inappropriate initiation declined in this group. Overall, the study demonstrates promising effects of the novel App-based digital intervention on verbal conversational skills in children with high function ASD.

• Korean Journal of Cognitive Science
• /
• v.17 no.2
• /
• pp.139-150
• /
• 2006

Speech recognition errors cause fatal results in a spoken dialogue system. When a system can not determine the speech-act of u utterance due to speech recognition errors, a dialogue system has a difficulty in continuing conversation. In this paper, we propose strategies for sub-dialogue generation by inferring the speech-act of an utterance with patterns of recognition errors on the field of form-filling dialogue. We used the proposed method on a plan-based dialogue model, corrected 27% of incomplete tasks, and acquired overall 89% of task completion rate.

• Annual Conference on Human and Language Technology
• /
• 1995.10a
• /
• pp.112-116
• /
• 1995

본 논문에서는 한-일 대화체 기계번역 시스템을 위한 대화체 모델을 제시한다. 이 대화체 모델에서는 구문분석과 의미분석을 거치지 않고 형태소 분석만을 이용하여 대화체 모델을 구현하였다. 대화체모델은 담화문으로부터 목표를 추출하는 GOAL DETECTOR, 추출된 목표에 맞는 플랜을 제시하는 PROPOSER, 제시된 플랜의 적합성 여부를 결정하는 PROJECTOR, 플랜의 실행 후 결과를 시스템의 환경에 반영하는 EXECUTOR 및 영역에 대한 지식을 표현하는 영역지식(Domain Knowledge)으로 구성이 된다.