• Information Systems Review
• /
• v.16 no.3
• /
• pp.49-68
• /
• 2014

These days, consumers have increasingly preferred to digital real-time streamlining and downloading to listen to music because this is convenient and affordable for the consumers. Accordingly, sales of music in compact disk formats have steadily declined. In this regards, online digital music has become a new communication channel to listen musics, where digital files can be delivered over various online networks to people's computing devices. The majority of online digital music distributors has Music Recommender Systems for sales of digital music on their websites. Music Recommender Systems are parts of information filtering systems that provide the ratings or preferences that users give to music. Korean online digital music distributors have Music Recommender Systems. But those online music distributors didn't provide any rules or clear procedures that recommend music. Therefore, we raise important questions as follows: "Is Music Recommender Systems Fair?", "What is the impact of Music Recommender Systems on online music rankings and sales?" While previous studies have focused on usefulness of Music Recommender Systems, this study investigates not only fairness of Current Music Recommender Systems but also Relationship between Music Recommender Systems and online Music Charts. This study examines these issues based on Bandwagon effect, ranking effect, Slot effect theories. For our empirical analysis, we selected the most famous five online digital music distributors in terms of market shares. We found that all recommended music is exposed to the top of 'daily music charts' in online digital music distributors' websites. We collected music ranking data and recommended music data from 'daily music chart' during a one month. The result shows that online music recommender systems are not fair, since they mainly recommend particular music that supported by a specific music production company. In addition, the recommended music are always exposed to the top of music ranking charts. We also find that recommended music usually appear at the top 20 ranking charts within one or two days. Also, the most music in the top 50 or 100 ranks are the recommended music. Moreover, recommended music usually remain the ranking charts more than one month while non-recommended music often disappear at the ranking charts within two week. Our study provides an important implication to online music industry. Because music recommender systems and music ranking charts are closely related, music distributors may improperly use their recommender systems to boost the sales of music that related to their own companies. Therefore, online digital music distributor must clearly announce the rules and procedures about music recommender systems for the better music industry.

• The Korean Publising Journal, Monthly
• /
• s.249
• /
• pp.16-17
• /
• 1999

새로운 세기를 앞둔 이즈음 세상에는 희망과 불안이 교차하고 있다. 그 가운데서도 지성사적인 공황은 다가올 21세기를 한층 어둡게 만들고 있다. "출판저널"은 21세기에도 여전히 그 빛을 발할 20세기의 고전을 뽑아 21세기로 가는 길목을 밝히는 가로등으로 삼고자 한다. 국내 각 분야 지식인 100인에게 비전공 분야를 포함한 15종씩 추천받았다. 3번 이상 중복추천된 양서 94선, 2번 이상 추천된 국내서 36선, 모두 130선을 소개한다. 한 저자의 책이 여러 종 추천된 경우 2회 이상 추천된 책만을 소개하는 것을 원칙으로 했다. 국내 번역된 책은 번역된 제목을 우선으로 했고, 미번역작은 원제를 달았다.

• 한국IT서비스학회:학술대회논문집
• /
• 2008.05a
• /
• pp.511-515
• /
• 2008

이웃기반 협력 필터링을 이용한 추천시스템은 적은 평가 자료로 인해 추천 성능에 문제가 생긴다. 이는 다른 고객의 정보도 추천에 사용하는 협력 필터링에서 이웃고객 선정에 문제가 생겨 추천시스템의 신뢰가 떨어진다. 본 논문은 추천시스템의 신뢰를 높이기 위한 방법으로 선호도 평가치가 적은 상품을 임계값을 이용하여 선별하고 이에 따라 고객의 표준편차를 조사하였다. 그리고 표준편차가 낮은 고객에 대한 MAE를 분석하여 예측의 정확도가 높아짐을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.372-375
• /
• 2018

본 논문은 온라인 음원 서비스 이용자들이 겪는 선택의 어려움을 최소화하고, 낭비되는 시간을 줄이기 위한 음악 추천 기법을 제안하고자 한다. 제안하는 기법은 개인정보의 이용 없이 아이템을 추천할 수 있는 아이템 기반 협업필터링 알고리즘을 사용한다. 더 정확한 추천을 위해 음원의 메타데이터를 이용한다. 실험을 통해 제안하는 기법이 메타데이터를 이용하지 않을 때보다 추천 성능이 향상되는 것을 확인하였다.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2014.08a
• /
• pp.7-10
• /
• 2014

이 연구에서는 음원 서비스의 이용자들이 공개앨범에서 추천한 음원 리스트에 특성가수와 동시출현한 곡들의 정보를 분석하여 특성가수의 이미지를 네트워크 기법으로 표현하였고 동시출현한 곡의 통계분석을 통하여 해당 가수를 선택한 이용자가 선호할 만한 연관 곡을 추천하고자 하였다. 분석결과 추천되는 음원리스트에 동시 출현되는 가수들의 장르적 특성으로 특정가수의 이미지가 표현되었고 시기별로 가수의 이미지가 변화되는 것이 추적되었다. 이 연구에서 제시된 방법은 이용자에게 변화하는 가수의 이미지에 따라 연관 정보를 유연하게 추천할 수 있는 방안으로 활용될 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.338-339
• /
• 2010

사용자가 원하는 정보를 자동으로 찾아내어 제공하는 추천시스템은 최근 사용자의 만족도를 높이기 위해 많은 연구들이 진행되고 있다. 본 논문은 사용자의 프로파일, 음식 주문 내용 및 날씨/온도 등 외부요인을 기반으로 의사 결정나무를 이용하여 개인의 선호도를 분석하고 연관규칙을 이용하여 음식의 연관성을 분석한 후 음식을 추천하는 유연성 있는 개인화 추천시스템을 제안하고 구축하였다. 본 시스템은 복수 전략 학습을 이용하여 추천함으로써 단일 학습방법을 사용했을 때보다 만족도가 높아지는 것을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.504-506
• /
• 2023

본 연구에서는 기존 여행지 추천의 플랫폼에 있어 개인의 취향에 맞는 여행지 추천이 어렵다는 점을 해결하고자, 비선형적 관계를 해결할 수 있는 NCF 심층신경망 추천시스템을 이용하여 개인의 성향에 따라 여행지를 추천해 주는 시스템을 제안하고 이를 평가한 결과를 보고한다.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.183-200
• /
• 2009

Collaborative Filtering is one of the most used recommender systems. However, basically it cannot be used to recommend new products to customers because it finds products only based on the purchasing history of each customer. In order to cope with this shortcoming, many researchers have proposed the hybrid recommender system, which is a combination of collaborative filtering and content-based filtering. Content-based filtering recommends the products whose attributes are similar to those of the products that the target customers prefer. However, the hybrid method is used only for the limited categories of products such as music and movie, which are the products whose attributes are easily extracted. Therefore it is essential to find a more effective approach to recommend to customers new products in any category. In this study, we propose a new recommendation method which applies centrality concept widely used to analyze the relational and structural characteristics in social network analysis. The new products are recommended to the customers who are highly likely to buy the products, based on the analysis of the relationships among products by using centrality. The recommendation process consists of following four steps; purchase similarity analysis, product network construction, centrality analysis, and new product recommendation. In order to evaluate the performance of this proposed method, sales data from H department store, one of the well.known department stores in Korea, is used.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.4
• /
• pp.127-152
• /
• 2021

The purpose of this study is to analyze the aspects of teacher librarians' book recommendation services for individual readers. For this purpose, data were collected through in-depth interviews with the teacher librarians of elementary school. Through the analysis of the collected data, the process of the teacher librarians' book recommendation, the main characteristics of the book recommendation, and the factors considering in the book recommendation, as well as information on major issues that arise in the book recommendation activity were derived and presented. Specifically, it was confirmed that the teacher librarians's book recommendation process was implemented in the following stages: questioning and interviewing, book recommendation, and follow-up. And, it was investigated that the factors considered when recommending books were students' interest, reading history, book fun, reading level, book level, teacher, class, and curriculum. In addition, it was confirmed that differences occurred in the experiences and perceptions of teacher librarians in the process of considering these factors. These results can provide the implications for resolving the problems of the teacher librarians who perform book recommendation services.

• 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.