• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.993-996
• /
• 2021

챗봇의 사용 용도는 일상 대화와 소비자 응대를 넘어서 심리 상담 용도로 확장하고 있다. 이 연구에서는 챗봇-사람 채팅에서 무작위로 추출한 '우울'과 관련된 대화 데이터를 텍스트마이닝 기법으로 분석하여 채팅에서의 우울 관련 담론 주제를 파악하였다. 더불어 정성 분석을 통해 사용자들이 챗봇에 털어놓고 있는 '우울' 의 종류를 범주화하고 분류하여, 트위터의 '우울' 데이터와의 차이점을 비교하였다. 이를 통해 챗봇 데이터의 '우울' 대화만의 특징을 파악하고, 우울 증상 탐지와 그에 따른 적절한 심리지원 정보를 제공하는 서비스 디자인의 착안점을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.1028-1030
• /
• 2022

실시간 보이스 채팅과 텍스트 채팅을 활용하여 양방향 비대면 행사 및 공연을 진행할 수 있다. 사용자의 개성을 나타낼 수 있는 캐릭터를 선택하여 덕성여자대학교 메타버스 캠퍼스를 탐방할 수 있다.

• Proceedings of the Korea Database Society Conference
• /
• 2001.11a
• /
• pp.323-338
• /
• 2001

o 사용자의 인터페이스(User Interface)고려 - 다운로드 없는 채팅 - 커넥션 오리엔티드 커뮤니케이션 도구 제공 - 기술력을 바탕으로 한 서비스 - 막대한 Scalability를 견뎌낼 수 있는 기술/운영적인 도전 (중략)

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2001.11a
• /
• pp.73-74
• /
• 2001

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.11a
• /
• pp.168-168
• /
• 2004

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.11a
• /
• pp.169-169
• /
• 2004

• Journal of Advanced Marine Engineering and Technology
• /
• v.37 no.2
• /
• pp.205-212
• /
• 2013

The previous chatting systems have generally used methods based on lexical agreement between users' input sentences and target sentences in a database. However, these methods often raise well-known lexical disagreement problems. To resolve some of lexical disagreement problems, we propose a three-step sentence searching method that is sequentially applied when the previous step is failed. The first step is to compare common keyword sequences between users' inputs and target sentences in the lexical level. The second step is to compare sentence types and semantic markers between users' input and target sentences in the semantic level. The last step is to match users's inputs against predefined lexico-syntactic patterns. In the experiments, the proposed method showed better response precision and user satisfaction rate than simple keyword matching methods.

• Journal of Creative Information Culture
• /
• v.7 no.2
• /
• pp.91-98
• /
• 2021

As the amount of time that elementary school students spend online increased due to Corona 19, the amount of posts, comments, and chats they write increased, and problems such as offending others' feelings or using swear words are occurring. Netiquette is being educated in elementary school, but training time is insufficient. In addition, it is difficult to expect changes in student behavior. So, technical support through natural language processing is needed. In this study, an experiment was conducted to automatically filter profanity sentences by applying them to a pre-trained language model on sentences written by elementary school students. In the experiment, chat details of elementary school 4-6 graders were collected on an online learning platform, and general sentences and profanity sentences were trained through a pre-learned language model. As a result of the experiment, as a result of classifying profanity sentences, it was analyzed that the precision was 75%. It has been shown that if the learning data is sufficiently supplemented, it can be sufficiently applied to the online platform used by elementary school students.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.384-399
• /
• 2021

This study aims to identify the characteristics and meanings that Korean musical enthusiasts take on as cultural intermediaries of musical content by analyzing the real-time conversations they have while watching musicals performed in online spaces. To this end, the 'Live TALK' chat during the 'ontact' (online contact) performance of the musical Marie Curie was observed in real-time and subsequently analyzed in terms of the characteristics of online cultural intermediaries: their owned capital, their mediating language, and their relationship with the consumers. As a result of the analysis, musical enthusiasts were found to possess a wealth of cultural capital based on practical experience and inquiry, and to be utilizing specific identifying expressions in their language use. In addition, they appeared to be interactive in their communication with the general audience, which could be seen in the flow of spontaneous conversations as well as questions and answers occurring in the live chat. This study is significant in confirming that musical enthusiasts are positioning themselves as new cultural intermediaries through their cultural practices: taking on the role of guides and mediators in the online space 'Live TALK.'

• Journal of Digital Forensics
• /
• v.12 no.3
• /
• pp.1-8
• /
• 2018

A random chat application is a type of social dating application that helps people find a lover or spouse by randomly connecting and providing services such as text, voice and video chat. Recently, there has been globally a rapid increase in its use due to the fact that it provides people to quick and convenient encounters at low cost. However, it is used as one of method to prostitute or to trade drugs and become a cause of violent crimes due to various criminal occurring after actual meeting between app users. For this reason, a random chat application is likely to provide proof of prostitution or drug trade and clues to arrest rape, kidnapping and murder suspects. Thus, it is necessary to analyse random chat applications from the viewpoint of digital forensics investigation, but there is no related research at all. Therefore, in this paper, we analyzed artifacts of 6 Korea random chat application's user behaviors; Ranchat, AngTalk, SsumgThing, DaTalk, EveryTalk and Sail. As a result, we found that it is remain on mobile device that time and contents of message transmission/reception, sender/receiver, friend profile and user account creation time when user is using the applications.