초록

This study proposes the analysis method in sentence semantics that can be automatically identified and processed as appropriate items in the system according to the composition of the sentences contained in the data corresponding to the logical semantic structure metadata of the research papers. In order to achieve the purpose, the structure of sentences corresponding to ‘Research Objectives’ and ‘Research Outcomes’ among the semantic structure metadata was analyzed based on the number of words, the link word types, the role of many-appeared words in sentences, and the end types of a word. As a result of this study, the number of words in the sentences was 38 in ‘Research Objectives’ and 212 in ‘Research Outcomes’. The link word types in ‘Research Objectives’ were occurred in the order such as Causality, Sequence, Equivalence, In-other-word/Summary relation, and the link word types in ‘Research Outcomes’ were appeared in the order such as Causality, Equivalence, Sequence, In-other-word/Summary relation. Analysis target words like ‘역할(Role)’, ‘요인(Factor)’ and ‘관계(Relation)’ played a similar role in both purpose and result part, but the role of ‘연구(Study)’ was little different. Finally, the verb endings in sentences were appeared many times such as ‘∼고자’, ‘∼였다’ in ‘Research Objectives’, and ‘∼었다’, ‘∼있다’, ‘∼였다’ in ‘Research Outcomes’. This study is significant as a fundamental research that can be utilized to automatically identify and input the metadata element reflecting the common logical semantics of research papers in order to support researchers’ scholarly sensemaking.

Abstract

초록

기록관의 역할이 커지고 있음에도 불구하고 아직 기록의 중요성에 대해 인지하지 못하는 잠재적 이용자가 많다. 이 연구에서는 이용자에 대한 기록정보서비스를 강화하기 위한 방법으로 기록관과 이용자의 상호작용을 지원하는 챗봇을 개발해보고자 하였다. 이에 챗봇의 구체적인 개발 절차와 방법을 살펴보고, 명지대학교 대학사료실을 사례로 이용자 요구 및 질의 분석을 진행하였으며, 챗봇 개발을 위한 논리적 구조 설계를 진행하였다. 이어 IBM Watson Conversation과 카카오톡 메신저를 통해 챗봇을 구축한 뒤, 시험 실행(Pilot run) 과정을 통해 챗봇과 이용자의 상호작용 과정을 확인하였다. 이러한 기록정보서비스 챗봇 개발 경험을 바탕으로, 챗봇 도입을 위한 수준 결정, 이용자 요구 분석, 챗봇 구축을 위한 도구 선정, 대화식 상호작용을 위한 구문 설정과 관련된 시사점을 제시하였다.

Abstract

The role of archives and records centers is expanding, however many potential users are not aware of the importance of the records and archives. As a method to improve the archival information services to users, in this study, we developed chatbot that supports the interaction between the users and the archives and records centers. Thus we examined the specific development procedures and methods, analyzed user requests and questions of the archives and records center of Myongji university as a case, and conducted a logical structure design for chatbot development. After building the chatbot based on IBM Watson Conversation and Kakaotalk messenger, we were able to find how the chatbot interacted with the users through a pilot run. Based on the experience of developing information service chatbot, the implications related the introduction of the chatbot were suggested which include determination of the level of the chatbot, analysis of the user requests, selection of the tool for the chatbot, and syntax setting for the conversational interaction.