• 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.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Information Systems Review
• /
• v.18 no.3
• /
• pp.155-183
• /
• 2016

Research on personalized recommender service that uses big data has gained considerable attention given the increasing volume of contents being created. This development indicates the need for service providers to collect personal information and content rating data to personalize content recommendations. Previous studies on this topic proposed algorithms to offer improved recommendations using minimal rating data or service designs and increase the number of ratings. However, limited studies have been conducted on the factors that motivate the ratings input of users, as well as the factors that influence their continuous usage of recommender service. The present study explored the factors that motivate users to enter ratings by conducting in-depth interviews with users who use recommender services. The meanings of these ratings were also explored. Results show that the meaning and usage range of ratings differed based on the stage of a user's with utilization of the service. When users input an initial rating, they treat such a rating as a database to save the impression of a past experience. Such a rating is then used as a tool to reflect the current feeling and thoughts of a user. In the end, users were not only interested in their own rating system, but they also actively sought out the meaning of the rating systems of others and utilized them. Users also expressed mistrust in the recommendations of the service because they were aware of the limitation of the algorithms. This study identified a number of practical implications regarding recommender services.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.745-747
• /
• 2023

여러 분야에서 인공지능 모델을 활용한 추천 방법들이 많이 사용되고 있다. 본 논문에서는 관광지의 대중적이고 정확한 추천을 위해 GPT-3 와 같은 생성 모델로 생성한 가상의 리뷰 문장을 통해 KoBERT 모델을 학습했다. 생성한 데이터를 통한 KoBERT 의 학습 정확도는 0.98, 테스트 정확도는 0.81 이고 실제 관광지별 리뷰 데이터를 활용해 관광지를 분류했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.534-535
• /
• 2020

본 논문에서는 딥러닝과 지식베이스를 융합하여 활용한 질환 인식 및 식품 추천 시스템을 제안한다. 제안하는 시스템은 온전히 모바일 디바이스 내에서 작동하는 시스템이다. 본 시스템은 압축된 딥러닝 모델을 이용해 사용자 대화 텍스트를 분석하여 사용자의 질환을 예측한다. 그 후, 지식베이스를 기반으로 해당 질환 관리에 도움이 되는 식품을 매칭하고 사용자에게 추천한다. 이는 사용자 친화적 헬스케어 애플리케이션으로써 체크리스트 작성 등 번거로운 작업 없이도 사용자에게 유용한 건강 정보를 제공할 수 있다.

• Archives of design research
• /
• v.16 no.2
• /
• pp.23-34
• /
• 2003

The need for personalized web site design has been increased these days. Current approach for personalized web site design is easily applied to web site with their cost-effective feature, but is hard to provide a more refined personalized service due to its lack of accumulation of user data. In this study, the design recommender system is investigated as a more advanced method for web site design personalization. We provide an overview of current recommender systems, and then outlined a newly developed design recommender system, which employs collaborative filtering technique to provide tailored recommendation for users.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.535-538
• /
• 2009

모바일 단말기 사용자 수의 증가와 위치기반 서비스 기술의 발달로 위치 정보를 활용한 다양한 위치 정보 서비스가 등장하고 있다. 친구들과 약속을 정하는 일은 빈번하게 일어난다. 약속을 정하기 위해서는 모든 친구에게 연락을 해야 하고 각자 선호하는 장소가 다르기 때문에 모든 친구들이 만족할 만한 최적의 장소를 찾기가 어렵다. 본 논문에서는 모바일 환경에서 친구의 위치를 파악하고 사용자와 친구의 성향을 파악하기 위해 협업 필터링과 인구통계학적 정보를 사용하였고, 약속 장소를 선정하기 위해 사용자와 친구의 위치를 기반으로 후보 영역을 선택하여 약속 장소와 시간을 추천하는 서비스를 제공함으로써 약속을 맺기 위한 절차를 간소화 할 뿐 아니라 사용자와 친구의 성향에 맞는 약속 장소를 추천하여 사용자와 친구가 만족 할 수 있는 약속을 형성할 수 있도록 하는 약속 장소, 시간 추천 서비스 시스템을 설계하였다.

• The Journal of Society for e-Business Studies
• /
• v.17 no.2
• /
• pp.129-147
• /
• 2012

Collaborative filtering (CF), one of the most successful recommendation techniques, has been used in a number of different applications such as recommending web pages, movies, music, articles and products. One of the critical issues in CF is why recommendation performances are different depending on application domains. However, prior literatures have focused on only data characteristics to explain the origin of the difference. Scant attentions have been paid to provide systematic explanation on the issue. To fill this research gap, this study attempts to systematically explain why recommendation performances are different using structural indexes of social network. For this purpose, we developed hypotheses regarding the relationships between structural indexes of social network and recommendation performance of collaboration filtering, and empirically tested them. Results of this study showed that density and inconclusiveness positively affected recommendation performance while clustering coefficient negatively affected it. This study can be used as stepping stone for understanding collaborative filtering recommendation performance. Furthermore, it might be helpful for managers to decide whether they adopt recommendation systems.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.187-196
• /
• 2021

The mobility handicapped are representative socially vulnerable people who account for a high percentage of our society. Due to the recent development of technology, personalized welfare technologies for the socially vulnerable are being studied, but it is relatively insufficient compared to the general people. In this study, we intend to implement a personalized restaurant recommendation system for the mobility handicapped. To this end, a hybrid recommendation system was implemented by combining the data of special transportation boarding and alighting history (7,153 cases) and information of Daegu Food restaurants (955 cases). In order to evaluate the effectiveness of the implemented recommendation system, we conducted performance comparisons with existing recommendation systems by prediction error rate and recommendation coverage. As a result of the analysis, the performance was higher than that of the existing recommendation system, and the possibility of a personalized restaurant recommendation system for the mobility handicapped was confirmed. In addition, we also confirmed the correlation in which similar restaurants are recommended in some types of the mobility handicapped. As a result of this study, it is judged that it will contribute to the use of restaurants with high satisfaction for the mobility handicapped, and the limitations of the study are also presented.

• 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.