• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.3
• /
• pp.343-372
• /
• 2021

The purpose of this study is to select keywords that can recommend books by personality type, and to test whether the chosen keywords can be actually used in the categorization and customized recommendation of books for each personality type. To achieve the research goal, this study chose books that match the level of fifth and sixth grade elementary school students and first grade middle school students and commissioned an expert group to categorize the books into groups that are preferred by each personality type. As a result of the classification, half of the books in which more than five experts agreed showed high consensus. In addition, the results of classifying books by personality type with keywords extracted by the automatic word extraction system by collecting the book review data of the selected books were similar to the results of the final judgement by the expert group, except for a few books. In conclusion, this study proved that it is possible to classify and recommend books that are likely to be preferred by different personality types using review keywords.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.617-624
• /
• 2001

With the proliferation of E-Commerce, product informations and services are provided to customers diversely. Thus customers want a software agent that can retrieve and recommend goods satisfying various purchase conditions as well as price. In this paper, we present a MAS (multi-agent system) for book information retrieval and recommendation in E-Commerce. User's preference is reflected in the MAS using the profile which is taken by user. The proposed MAS is composed of individual agents that support information retrieval, information recommendation, user interface, and web robots and a coordination agent which performs information sharing and job management between individual agents. Our goal is to design and implement this multi-agent system on a Windows NT server. Owing to the workflow management of the coordination agent, we can remove redundant information retrievals of web robots. From the results, we could provide customers various purchase conditions for several online bookstores in real-time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.18-21
• /
• 2015

정보의 양이 막대한 요즘, 독자가 원하는 도서를 추천해주기 위해서는 독자의 성향을 파악할 필요가 있다. 본 논문에서는 정의된 독자 프로파일을 기반으로 독자의 성향을 분석하고, 추가로 피드백 정보가 사용가능 할 경우 독자의 성향을 다시 보완하여 분석하는 방법에 대해 제안하였다. 독자의 성향은 도서관이나 서점 등에서 일반적으로 사용하는 대표적인 도서 분류인 카테고리를 사용하며, 성향 분석을 위한 피드백 정보로는 가장 정량적 신뢰도가 높은 구매내역 정보를 사용하여 독자에게 원하는 도서가 추천되도록 하는 방법을 제안한다. 제안된 분석을 적용하기 위하여 실제 온라인 서점에서 보유한 독자 프로파일을 사용하여 실험 결과를 도출하였다.

• Journal of Korean Library and Information Science Society
• /
• v.47 no.1
• /
• pp.279-303
• /
• 2016

This study proposes the Book-Curation service as part of the information service offered through school library websites. Also, this study aims to establish recommendation standards for curation prior to detailed system planning. For such service, the following tasks were carried out. First, the list of recommended books of existing systems were analyzed to identify the attributes that can be used for recommendation in the user and book information. Second, the analyzed attributes were utilized to establish 12 recommendation standards. Finally, a survey was carried out to identify the user preferences as to each standards. The results are as follows. First, the majority of students responded that curation service is necessary for using a library. Second, the top three standards are as follows: "best lending books based on the keywords of individual users"; "best lending books of the same year students"; "best lending books on the textbook-related reference booklist".

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1097-1104
• /
• 2011

In this paper, we propose a semantic web approach for personalized book recommendation. Our approach takes advantage of the content-based recommendation and improves its disadvantage that users should input their interesting fields into all book search systems they use. Our approach provides the sharing of users' profile with their interesting fields by enabling user's interesting fields to be described over each book classification ontology of various book information providers. We also provide a middleware that manages users' profiles written in RDF and analizes similarity between user's interesting field and each concept over the book classification ontology. Our approach provide better performance than traditional keyword-based search by sharing the user's profile among book recommendation systems.

• Journal of Korean Library and Information Science Society
• /
• v.53 no.4
• /
• pp.189-209
• /
• 2022

The purpose of this study is to analyze the content of the online book curation services and recommended books list by public libraries in Korea and to identify their properties. The case for analysis is a list of 11,447 recommended books provided by 35 online book curation services collected from 23 public libraries and the main results of the study are as follows. Only few case libraries were presenting recommendation themes, and recommendation targets were most often not specific, and the recommendation cycle of books was the most monthly. In general, books recommended for book curation do not overlap with each other, but there was overlap in the field of literature (novels) published in 2019~2021. For recommended books, the proportion of books published by some publishers was high, and books published in 2019~2021 were the most common. The subject areas analyzed based on the KDC 6th ed were literature the most. Readers analyzed by ISBN were of in the order of cultural books and children's books, and the type of publication was in the order of books, pucture books, and comics. Based on these research results, it was required to develop guidelines for online book curation service for public libraries and build a platform to share with libraries.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.601-604
• /
• 2001

도서 정보 추천 시스템에서 기존 사용자들의 정보를 이용하여 마이닝 기법중 군집 분석을 적용하여 사이트에 처음으로 접속하는 사용자와 접속률이 낮아 피드백 정보가 많이 없고 적절한 추천을 하지 못하는 사용자에게 비슷한 군집의 사용자들의 정보를 이용하여 적절한 정보를 추천한다. 본 논문에서는 기존의 멀티에이전트 추천 시스템에 데이터 마이닝 에이전트와 패턴 분석 에이전트를 접목하여 더 나은 추천 정보를 제공하기 위한 시스템을 제안한다.

• Journal of the Korean Society for information Management
• /
• v.39 no.3
• /
• pp.1-22
• /
• 2022

The purpose of this study is to propose a book recommendation system that can be used in school libraries. The book recommendation system applies an algorithm based on association rules using DLS lending data and is designed to provide personalized book recommendation services to school library users. For this purpose, association rules based on the Apriori algorithm and betweenness centrality analysis were applied and detailed functions such as descriptive statistics, generation of association rules, student-centered recommendation, and book-centered recommendation were materialized. Subsequently, opinions on the use of the book recommendation system were investigated through in-depth interviews with teacher librarians. As a result of the investigation, opinions on the necessity and difficulty of book recommendation, student responses, differences from existing recommendation methods, utilization methods, and improvements were confirmed and based on this, the following discussions were proposed. First, it is necessary to provide long-term lending data to understand the characteristics of each school. Second, it is necessary to discuss the data integration plan by region or school characteristics. Third, It is necessary to establish a book recommendation system provided by the Comprehensive Support System for Reading Education. Based on the contents proposed in this study, it is expected that various discussions will be made on the application of a personalization recommendation system that can be used in the school library in the future.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.147-150
• /
• 2015

감성은 개인적인 생활경험을 통해 표현되며 동일한 감정상태와 정보자극을 주더라도 다른 감성이 발생될 뿐만 아니라 개인, 사회, 문화 요인에 따라서 크게 변한다. 따라서 다른 영역의 감성과 도서에 대한 감성이 같지 않기 때문에 별도의 감성 사전 구축이 필요하다. 구축된 감성사전은 비슷한 성향의 도서와 사람을 묶어 추천해 주는데 활용할 수 있다. 감성 사전 구축을 위한 원천 정보로 네티즌이 책을 읽고 호감도와 함께 짧은 문장으로 쓴 소감을 활용하였다. 감성분석에서 가장 기본이 되는 분류는 긍정과 부정으로 나누는 것이다. 하지만, 실제로 도서를 추천하기위해서 긍정과 부정으로만 구분하는 것은 충분하지 않다. 따라서 본 연구에서는 도서에 대해서 감성을 긍정과 부정의 호감정도와 감성의 활성도를 조합한 8개의 감성으로 분류하고 각각의 지수를 함께 산출하여 감성어 사전을 구축하고 활용하는 방안을 제시하였다.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.3
• /
• pp.287-311
• /
• 2021

It is not easy for information users to find books that are suitable for them in a knowledge information society. There is a growing need for libraries to break away from traditional services and provide user-tailored recommendation services, but there are few qualitative studies on user satisfaction so far. In this study, a user-customized book recommendation was performed by applying Apriori, a correlation analysis algorithm, and satisfaction factors were analyzed in depth through interviews. The experimental data was the loan data of 100 people who used the most frequently used loan data for 10 years from 2009 to 2019 of the S library in Seoul. The interviewees of the experiment were those who could be interviewed in depth. After the correlation analysis, the concepts and categories derived by analyzing the interview data were 59 concepts, 6 sub-categories, and 2 upper categories, respectively. The upper categories were 'reading' and 'book recommendation service'. In the 'reading' category, there were 16 concepts of motivation for reading, 8 concepts of preferred books, and 12 concepts of expected effects. Also, in the category of 'reading recommendation service', there were 10 'reflection factors', 4 'reflection methods', and 9 'satisfaction factors'.