• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.34 no.4
• /
• pp.101-124
• /
• 2023

Book recommendations in libraries can be used as a tool to help users with vague needs browse and select books. Therefore, libraries spend a lot of time and effort to introduce various materials to their users and recommend suitable books. Meanwhile, various organizations other than libraries also publish recommended reading lists, and these lists reflect the intentions of the entity that selects the recommended books. The purpose of this study is finding out how the recommended book lists of libraries differ from the recommended reading lists of non-library organizations. To achieve this, the study limited the scope to 'teenagers', who are the main target audience for book recommendations in many organizations, and compared the recommended book lists of libraries and non-library organizations in terms of (1) the selection criteria for recommended books, (2) the characteristics of recommended books, and (3) the way of providing recommended book lists. Through this analysis, the study identified the characteristics and limitations of library recommended book lists and discussed areas for improvement.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.582-587
• /
• 2021

Book recommender system, which suggests book to users according to their book taste and preference effectively improves users' book-reading experience and exposes them to variety of books. Insufficient dataset of book rating records by users degrades the quality of recommendation. In this study, we suggest a book recommendation system that makes use of user's book ratings collaboratively with user's movie ratings where more abundant datasets are available. Through comprehensive experiment, we prove that our methods improve the recommendation quality and effectively recommends more diverse kind of books. In addition, this will be the first attempt for book recommendation system to utilize movie rating data, which is from the media-platform other than books.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.3
• /
• pp.5-26
• /
• 2022

The purpose of this study is to analyze high school students' understanding and use of the recommended books lists. The survey distributed to high school students in seven high schools located in Seoul, and 311 students responded. Using SPSS 24, the data was analyzed by frequency, binary logistic model, and one-way ANOVA. Results show the followings. First, the meaningful factors affecting students' use of recommended books lists are gender, grade levels, and the degree to which students think recommended books lists include the books that are suitable and interesting. Particularly, the degree to which students think recommended books lists include the suitable books for them is the strong factor affecting students' use of the recommended books lists. Second, male students are less likely to use recommended books lists than female students. Male students consistently are less likely to use the recommended books lists made by school librarians, subject teachers, and reading experts and/or organizations. Third, teacher-librarians believed that the recommended books lists would help students who do not enjoy reading and have difficulties in reading. However, the study finds that students who enjoy reading and read well are more willing to use the recommended books lists made by school librarians, subjects teachers, and reading experts and/or organizations than those who do not. Fourth, students are most willing to use the recommended books lists for college preparation. The findings suggest the further research topics in designing the recommended books lists suitable for high school students and in scaffolding the high school students' use of book information reflected in recommended books lists.

• Journal of Science Education
• /
• v.39 no.3
• /
• pp.434-445
• /
• 2015

In this study, science recommended books for elementary school students were analyzed. For the study, the screening tool with a number of criteria was produced. In order to develope a screening tool, we examined several previous studies and references. After that, through discussion and exchange of opinions, the preliminary screening tool was made. In order to ensure the reliability and validity, the pilot test was conducted. Then, detailing questions and modifications have been made by exchange of ideas. And nine science recommended books were analyzed. The results are as follows. First, as a result of examining recommended books, exploration and the nature of science were received a low rating. Second, description of the scientific knowledge was not sufficient. This discussion can be obtained through the following. First, when selecting recommended books, care should be taken in exploration and the nature of science. Second, a wide range of science trade books needs to study more.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.23-26
• /
• 2015

도서 정보 양이 급증하면서 사용자 성향과 선호도에 맞는 정보를 추천해주는 서비스의 중요성이 높아지고 있으며, 이와 관련하여 도서를 추천해주는 플랫폼 연구가 활발하게 진행되고 있다. 독자에게 성향과 선호도에 맞는 추천을 해주기 위해서는 사용자, 도서, 저자 등을 대상으로 하는 분석이 필요하며, 분석된 정보를 사용자에게 직관적으로 제공해주는 것이 필요하다. 따라서 본 논문에서는 저자에 대한 도서 정보를 시계열적으로 분석하고, 분석된 결과를 사용자에게 직관적으로 제공하는 시각화 방법을 제안한다. 제안한 방법은 저자의 도서를 시계열 방식으로 분석하고, 이를 시간 시각화와 레이더차트를 사용하여 도서정보를 제공한다. 또한 시간 시각화와 레이더 차트를 통해 두 저자의 도서 일대기와 분류의 변화를 직관적으로 확인할 수 있다.

• The Korean Publising Journal, Monthly
• /
• s.225
• /
• pp.23-23
• /
• 1997

제30회 '문화체육부 추천도서'가 선정됐다. 총류와 역사 종교.철학.문학 등 10개 분야에 걸쳐 총 112종 246책이 선정됐다. 올해는 특히 번역 분야를 새로 설정, 우리 문화를 세계에 널리 알리는 데 기여한 도서도 2종 선정돼 눈길을 끈다. 추천 목록은 다음과 같다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.363-364
• /
• 2023

카테고리별 베스트셀러를 통해 트렌드 파악 및 사용자 맞춤형 도서 추천을 위해 카테고리별로 도서 데이터를 수집하고, 대용량 데이터인 위키피디어 데이터를 이용하여 워드임베딩 모델을 구축한다. 도서 데이터에 대한 키워드 분석 및 LDA 주제분석 기법에 의해 카테고리별 핵심 단어 분석을 통해 도서 트렌드를 파악하고, 사용자 맞춤형 도서 정보 제공 및 도서를 추천하는 기능을 구현한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1177-1179
• /
• 2015

최근, 수많은 종류의 도서가 출판되고 있다. 또한 도서의 분야와 장르, 종류가 다양해지고 그 양 역시도 방대해지고 있다. 이러한 상황에서 사용자에게 적절한 도서를 고르기란 어려운 일이다. 본 논문에서는 보다 편리하고 적절한 도서 선택을 위해 도서추천시스템을 제안한다. 사용자의 나이와 성별, 국내/외도서, 선호 장르에 가중치를 부여하고 협업필터링을 사용하는 추천 시스템을 제안한다.

• Journal of Information Management
• /
• v.33 no.1
• /
• pp.1-17
• /
• 2002

This study examined several recommendation techniques to construct an effective book recommender system in a library. Experiments revealed that a hybrid recommendation technique is more effective than either collaborative filtering or content-based filtering technique in recommending books to be borrowed in an academic library setting. The recommendation technique based on association rule turned out the lowest in performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.14-17
• /
• 2015

오늘날 인터넷의 발달과 전자 책(e-Book) 시장규모가 커짐에 따라 온라인을 통한 도서 정보 제공이 증가하고 있다. 하지만 현재 도서 정보나 도서 추천을 제공하는 온라인 사이트들은 기본 서지 정보만을 위주로 제공하고 있어 도서 본문을 활용한 정보 제공 및 추천 시스템의 필요성이 증가하고 있다. 따라서 본 논문에서는 도서 본문을 활용한 정보 제공 및 개인 맞춤형 추천을 위해 '도서 정보 본문텍스트 통합 마이닝 기반 사용자 참여형 시각화 및 추천 큐레이션 플랫폼'을 제안하고, 이를 구축하였다. 제안한 서비스 플랫폼은 독자에게 다양한 방법으로 도서 정보를 제공하며, 독자는 적은 시간으로 많은 정보를 얻을 수 있도록 하여 사용자의 도서 선택의 폭을 넓혀줄 것이다.