• Asia pacific journal of information systems
• /
• v.29 no.3
• /
• pp.468-488
• /
• 2019

As the growth of online travel agencies (hereafter OTAs) accelerates, competition among hotels to gain exposure on the first page of OTA websites, and the financial burden, such as commissions hotels have to pay in return, are increasing. Therefore, to facilitate successful management in the tourism industry, it is important to establish what makes people continue the practice of using OTAs to book rooms in hotels and other accommodation outlets. By adopting the heuristic-systematic model (HSM), this study explores the factors that drive consumers' continued use of OTA and classifies them into heuristic cues (brand awareness, cost saving, and scarcity message) and systematic cues (recommendation quality and the ability to provide reputation). Furthermore, we divided the sample based on the location of hotels within and outside Korea, and investigated the different roles of the cues between two models. The results are expected to provide theoretical and practical implications for both OTAs and hotels.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.544-545
• /
• 2024

최근 성인 독서량은 지속적으로 감소하는데 비해 영상 콘텐츠 소비가 증가하고 있다. 이에 따라 새로운 사용자에 대한 선호도 및 행동 패턴에 대한 정보가 없고 새로운 도서에 대한 사용자 평가나 구매 정보가 부족해 콜드 스타트 문제와 데이터 희소성 문제가 발생하고 있다. 본 논문에서는 영상물 콘텐츠 기반 도서 하이브리드 추천 시스템을 제안하였다. 제안하는 추천 시스템은 영상물의 콘텐츠를 활용하여 콜드 스타트 문제와 데이터 희소성 문제를 해결할 수 있을 뿐만 아니라, 전통적인 도서 추천 시스템에 비해 성능이 향상되었고 장르, 줄거리, 평점 정보 기반 사용자 취향 정보까지 모두 반영된 질 높은 추천 결과까지 확인할 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.139-152
• /
• 2011

Recommender systems have become an important research field since the emergence of the first paper on collaborative filtering in the mid-1990s. In general, recommender systems are defined as the supporting systems which help users to find information, products, or services (such as books, movies, music, digital products, web sites, and TV programs) by aggregating and analyzing suggestions from other users, which mean reviews from various authorities, and user attributes. However, as academic researches on recommender systems have increased significantly over the last ten years, more researches are required to be applicable in the real world situation. Because research field on recommender systems is still wide and less mature than other research fields. Accordingly, the existing articles on recommender systems need to be reviewed toward the next generation of recommender systems. However, it would be not easy to confine the recommender system researches to specific disciplines, considering the nature of the recommender system researches. So, we reviewed all articles on recommender systems from 37 journals which were published from 2001 to 2010. The 37 journals are selected from top 125 journals of the MIS Journal Rankings. Also, the literature search was based on the descriptors "Recommender system", "Recommendation system", "Personalization system", "Collaborative filtering" and "Contents filtering". The full text of each article was reviewed to eliminate the article that was not actually related to recommender systems. Many of articles were excluded because the articles such as Conference papers, master's and doctoral dissertations, textbook, unpublished working papers, non-English publication papers and news were unfit for our research. We classified articles by year of publication, journals, recommendation fields, and data mining techniques. The recommendation fields and data mining techniques of 187 articles are reviewed and classified into eight recommendation fields (book, document, image, movie, music, shopping, TV program, and others) and eight data mining techniques (association rule, clustering, decision tree, k-nearest neighbor, link analysis, neural network, regression, and other heuristic methods). The results represented in this paper have several significant implications. First, based on previous publication rates, the interest in the recommender system related research will grow significantly in the future. Second, 49 articles are related to movie recommendation whereas image and TV program recommendation are identified in only 6 articles. This result has been caused by the easy use of MovieLens data set. So, it is necessary to prepare data set of other fields. Third, recently social network analysis has been used in the various applications. However studies on recommender systems using social network analysis are deficient. Henceforth, we expect that new recommendation approaches using social network analysis will be developed in the recommender systems. So, it will be an interesting and further research area to evaluate the recommendation system researches using social method analysis. This result provides trend of recommender system researches by examining the published literature, and provides practitioners and researchers with insight and future direction on recommender systems. We hope that this research helps anyone who is interested in recommender systems research to gain insight for future research.

• Journal of Internet Computing and Services
• /
• v.12 no.2
• /
• pp.85-101
• /
• 2011

The recommender system analyzes users' preference and predicts the users' preference to items in order to recommend various items such as book, movie and music for the users. The collaborative filtering method is used most widely in the recommender system. The method uses rating information of similar users when recommending items for the target users. Performance of the collaborative filtering-based recommendation is lowered when attacker maliciously manipulates the rating information on items. This kind of malicious act on a recommender system is called 'Recommendation Attack'. When the evaluation data that are in continuous change are analyzed in the perspective of data stream, it is possible to predict attack on the recommender system. In this paper, we will suggest the method to detect attack on the recommender system by using the stream trend of the item evaluation in the collaborative filtering-based recommender system. Since the information on item evaluation included in the evaluation data tends to change frequently according to passage of time, the measurement of changes in item evaluation in a fixed period of time can enable detection of attack on the recommender system. The method suggested in this paper is to compare the evaluation stream that is entered continuously with the normal stream trend in the test cycle for attack detection with a view to detecting the abnormal stream trend. The proposed method can enhance operability of the recommender system and re-usability of the evaluation data. The effectiveness of the method was verified in various experiments.

• Journal of Korean Library and Information Science Society
• /
• v.54 no.4
• /
• pp.255-279
• /
• 2023

The purpose of this study is to derive implications through a comparison of the current status of catalog enriched content services provision in U.S. public libraries and domestic public libraries. In addition, we are seeking ways to improve the catalog enriched content services for domestic public libraries in the future. From early September to mid-October 2023, specific books were searched on public library websites in the U.S. and Korea, and the functions of the enriched content services shown in the search results were compared. The results are as follows: First, domestic public library enriched content services require a separate company to develop and provide an enriched content services solution. Second, the enriched content services platform must discover domestic information sources that can be utilized in the areas of book-centered, book recommendation, and community engagement. Third, it is necessary to develop enriched content using public data such as the Library Information Naru. Fourth, each integrated library must that data generated from local community engagement services can be utilized as an enriced content service.

• Journal of the Korean Society for information Management
• /
• v.38 no.3
• /
• pp.311-334
• /
• 2021

The purpose of this study is to present the theoretical basis and quantified objective standards for the establishment of collection management policy. The study results are summarized as follows. Most of the study books were in the form of periodicals as a steady seller. Most of the steady sellers were textbooks which published periodically. As a modern novel, a steady seller was able to confirm the phenomenon of dependence on a specific author. Bestsellers were investigated to be influenced by publishers and authors. Books of publishers that publish comics and children's textbooks had a significant correlation with the selection of bestsellers. The average number of recommended books borrowed per recommended book was 14,871. The average number of loans per book selected as a bestseller was 53,531. Based on the loan data, about 80-82% of all top-tier loans were covered by 90%, and about 27-29% of all top-ranked loans were covered by 50%. This shows that the Pareto Principle can be firmly applied to public library lending patterns. Loans in the field of literature accounted for 50.6% of the total loans. Among literature, Korean literature accounted for 51.3% of the total. The natural sciences were generating more loans with a relatively small pool of literature compared to other subject fields.

• Knowledge Management Research
• /
• v.21 no.1
• /
• pp.117-136
• /
• 2020

In the studies for the recommender systems which solve the information overload problem of users, the use of transactional data has been continuously tried. Especially, because the firms can easily obtain transactional data along with the development of IoT technologies, transaction-based recommender systems are recently used in various areas. However, the use of transactional data has limitations that it is hard to reflect domain knowledge and they do not directly show user preferences for individual items. Therefore, in this study, we propose a method applying the word embedding in the transaction-based recommender system to reflect preference differences among users and domain knowledge. Our approach is based on SAR, which shows high performance in the recommender systems, and we improved its components by using FastText, one of the word embedding techniques. Experimental results show that the reflection of domain knowledge and preference difference has a significant effect on the performance of recommender systems. Therefore, we expect our study to contribute to the improvement of the transaction-based recommender systems and to suggest the expansion of data used in the recommender system.

• Journal of Korean Library and Information Science Society
• /
• v.43 no.3
• /
• pp.353-384
• /
• 2012

This study was conducted on the observation that the filter bubble and privacy violation problems are related to the personalized services provided by libraries. This study discussed whether there is the possibility for invasion of privacy when libraries provide services utilizing state-of-the-art technology, such as location-based services, context aware services, RFID-based services, Cloud Services, and book recommendation services. In addition, this study discussed the following three aspects: whether or not users give up their right to privacy when they provide personal information for online services, whether or not there are discussions about users' privacy in domestic libraries, and what kind of risks the filter bubble problem can cause library users and what are possible solutions. This study represents early-stage research on library privacy in Korea, and can be used as basic data for privacy research.

• Child Health Nursing Research
• /
• v.9 no.4
• /
• pp.408-419
• /
• 2003

Purpose: This study was done to develop a reliable and appropriate evaluation tool for sexual educational materials and to apply it to video materials for recommendation of excellent materials. Method: The items of the content for evaluation were based on the previous studies on the sexual education and evaluation tools. After testing validity and reliability of tool, final evaluation tool for sexual educational materials was developed. The evaluation tool was applied to 84 video materials and the excellent materials were recommended. Result: The final evaluation tool for sexual educational materials which consisted of two parts was developed. One is the evaluation of basic information which includes 8 items: target population, type of materials, producer, year of production, subject, theme, running time, and guide book. The other is the evaluation of content which includes 36 items related to characteristics of material, purpose, efficiency and scope of content. After applying the tool to 84 video materials, 39 excellent sexual education materials were suggested. Conclusion: The systematic development of materials for sexual education appropriate to the specific subjects should be done. Producers should describe the basic information on the outside of materials. For recommending the excellent materials, the periodical standardized evaluation of sexual educational materials should be done, and the database of the excellent materials should be provided for further utilization.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.27-44
• /
• 2020

In order to solve the user's information overload problem, recommender systems infer users' preferences and suggest items that match them. The collaborative filtering (CF), the most successful recommendation algorithm, has been improving performance until recently and applied to various business domains. Visual information, such as book covers, could influence consumers' purchase decision making. However, CF-based recommender systems have rarely considered for visual information. In this study, we propose VizNCS, a CF-based deep learning model that uses visual information as additional information. VizNCS consists of two phases. In the first phase, we build convolutional neural networks (CNN) to extract visual features from image data. In the second phase, we supply the visual features to the NCF model that is known to easy to extend to other information among the deep learning-based recommendation systems. As the results of the performance comparison experiments, VizNCS showed higher performance than the vanilla NCF. We also conducted an additional experiment to see if the visual information affects differently depending on the product category. The result enables us to identify which categories were affected and which were not. We expect VizNCS to improve the recommender system performance and expand the recommender system's data source to visual information.