• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.1078-1081
• /
• 2010

웹 2.0의 영향으로 인터넷 상에 범람하는 컨텐츠를 이용함에 있어 태깅 시스템은 매우 유연하고 효과적인 분류를 가능케 한다. 대부분의 웹 2.0 사이트에서는 검색된 정보에 해당하는 태그와 연관성이 있는 태그를 나타냄으로써 또 다른 관련 컨텐츠를 이용할 수 있는 서비스를 제공한다. 컨텐츠 사용자에 의해 생성되는 태그는 개인 성향에 따라 동일 컨텐츠에 다양하게 적용될 수 있으며 이로 인해 태그를 이용한 검색은 낮은 정확도를 나타낼 수 있다. 본 논문에서는 태그 선택에 있어 인간 상호작용의 특성을 파악하여 개인이 선호하고, 필요로 하는 컨텐츠에 대한 태그를 추천할 수 있는 태그 가치 측정 알고리즘을 제안한다. 컨텐츠 선택에 있어 의사결정에 영향을 미치는 요인을 식별하고 선호영화 추천 서비스인 MovieLens 사이트의 데이터 셋을 적용하여 태그 추천의 예측 정확도를 비교 평가함으로써 향상된 태그 가치 산정 결과를 제시한다.

• Journal of Broadcast Engineering
• /
• v.18 no.1
• /
• pp.88-97
• /
• 2013

Collaborative filtering(CF) for the personalized recommendation is a successful and popular method in recommender systems. But the mainly researched and implemented cases focus on dealing with independent items with explicit feedback by users. For the domain of TV program recommendation in VOD service platform, we need to consider the unique characteristic and constraints of the domain. In this paper, we studied on the way to convert the viewing history of each TV program episodes to the TV program preference by considering the series structure of TV program. The former is implicit for personalized preference, but the latter tells quite explicitly about the persistent preference. Collaborative filtering is done by the unit of series while data gathering and final recommendation is done by the unit of episodes. As a result, we modified CF to make it more suitable for the domain of TV program VOD recommendation. Our experimental study shows that it is more precise in performance, yet more compact in calculation compared to the plain CF approaches. It can be combined with other existing CF techniques as an algorithm module.

• Journal of the Korean Society for Library and Information Science
• /
• v.54 no.4
• /
• pp.147-167
• /
• 2020

The purpose of this study is to analyze the factors influencing the intention of revisiting and recommending by applying a structural equation model, targeting the service quality factors of university libraries derived from previous studies. For 11 days from April 30th, 2020 to May 10th, 2020, a total of 127 user groups (undergraduate students, graduate students, professors/instructors) were surveyed on their intention to revisit and recommend. The analysis results are as follows. 'Materials' and 'service customization' were shown as quality dimensions that influence revisit. In addition, revisiting was found to have an effect on recommendation intention, and it was analyzed that 'materials' and 'service customization' affect not only revisit but also recommendation intention. In addition, 'service customization' was found to be a factor that directly affects the intention to recommend. Based on this, a method of applying the concept of customization to library services and marketing was proposed in an environment where users' needs are diversifying and becoming personalized.

• Journal of the Korean Society for information Management
• /
• v.20 no.4 s.50
• /
• pp.113-134
• /
• 2003

With SDI service provided in libraries and information centers traditionally, this paper studies component technologies and structure of system platform in PIS(personalization information service based on the customized information service served currently in some institutions. The PIS system should provide relevant information as an output through the learning system analyzing user information searching behavior as an input value with personal profile information. To do it, this paper studies requirements and algorithms to develop PIS, and proposes learning system and recommendation system as core components in PIS.

• The Journal of the Korea Contents Association
• /
• v.17 no.11
• /
• pp.183-191
• /
• 2017

In order to secure the convenience of information retrieval by users of scientific information service platforms and to reduce the time required to acquire the proper information, this study proposes an optimized content recommendation algorithm among the algorithms that currently provide service menus and content information for each service, and conducts comparative evaluation on the results. To enhance the recommendation accuracy, users' major items were added to the original algorithm, and performance evaluations on the recommendation results from the original and optimized algorithms were performed. As a result of this evaluation, we found that the relevance of the content provided to the users through the optimized algorithm was increased by 21.2%. This study proposes a method to shorten the information acquisition time and extend the life cycle of the results as valuable information by automatically computing and providing content suitable for users in the system for each service menu.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.206-207
• /
• 2018

방대한 정보를 사용자에게 제공하기 위해 검색 엔진은 다양한 알고리즘을 통해 사용자마다의 최적화된 정보를 구성한다. 과제, 논문, 특허, 연구보고서 등 과학기술정보를 서비스 하는 주체 역시 나름의 검색 알고리즘으로 정보를 제공하지만, 질의어와 문서간의 적합도만을 측정하여 검색 결과를 제시할 뿐 사용자의 관심 분야나 요구를 반영하지 않고 있다. 특히 관심 분야에 적합한 과학기술정보를 사용자가 접근하기 쉽게 제공하는 것은 매우 중요하다. 본 논문에서는 사용자 관심분야를 서비스 이용행태로부터 결정하여 이를 과학기술정보 개인화에 반영하는 서비스에 대해 제안하였다. 이를 위해 실시간 관심분야 추적, 관심 태그 클라우드 제공, 관심분야 기반 추천정보 제공, 검색 결과 개인화 네 가지 기능으로 구성된 과학기술정보 개인화 서비스를 설계하고 구현하였다.

• The Journal of the Korea Contents Association
• /
• v.19 no.2
• /
• pp.284-295
• /
• 2019

In the recent times, a personalized travel path recommendation based on both travelogues and community contributed photos and the heterogeneous meta-data (tags, geographical locations, and date taken) which are associated with photos have been studied. The travellers using social media leave their location history, in the form of paths. These paths can be bridged for acquiring information, required, for future recommendation, for the future travellers, who are new to that location, providing all sort of information. In this paper, we propose a personalized travel path recommendation scheme, based on social life log. By taking advantage, of two kinds of social media, such as travelogue and community contributed photos, the proposed scheme, can not only be personalized to user's travel interest, but also be able to recommend, a travel path rather than individual Points of Interest (POIs). The proposed personalized travel route recommendation method consists of two steps, which are: pruning POI pruning step and creating travel path step. In the POI pruning step, candidate paths are created by the POI derived. In the creating travel path step, the proposed scheme creates the paths considering the user's interest, cost, time, season of the topic for more meaningful recommendation.

• Information Systems Review
• /
• v.25 no.4
• /
• pp.67-87
• /
• 2023

Many online shopping sites now offer personalized recommendation systems to improve consumers' shopping experiences by lowering costs (time, cost, etc.), catering to consumers' tastes, and stimulating consumers' potential shopping needs. So far, domestic and foreign research on the personalized recommendation system has mainly focused on the field of computer science, which is advantageous for obtaining accurate personalized recommendation results for users but difficult to continuously track the users' psychological states or behavioral intentions. This study attempted to investigate the effect of the characteristics of the personalized recommendation system in the online shopping environment on consumer perception and purchase intention for consumers using the Stimulus-Organism-Response (S-O-R) model. The analysis results adopted all hypotheses on the effect of the quality of the personalized recommendation system and information quality on trust and perceived value. Through the empirical results of this study, the factors influencing consumers' use of personalized recommendation system can be identified. In order to increase more purchase, online shopping companies need to understand consumers' tastes and improve the quality of the personalized system by improving the recommendation algorithm thus to provide more information about products.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1549-1552
• /
• 2015

최근 스마트폰을 비롯한 스마트 디바이스의 급격한 보급화가 이루어짐에 따라 추천가 시스템과 같은 개인화 서비스에 관한 연구가 활발히 진행되고 있다. 그러나 이러한 서비스는 활용 방안이 광범위함에도 불구하고 마케팅 등의 특정 분야에 한정되어 있거나 저수준의 QoS를 제공하는 정도에 머물러 있어 국내의 추천가 시스템은 아직 도입단계에 불과하다. 추천가 시스템은 추천할 물품과 같은 객체의 기본 및 평가 정보를 텍스트 형태의 메타 정보로 나타낸다. 이러한 메타 정보 기반 필터링에 의해 주변 경로 및 취향이 고려되지 않은 결과를 사용자에게 제공하고 있다. 이에 사용자와 상호작용하여 건강이나 취향, 식사 이력, 통계 등을 고려해 메뉴를 추천해주는 최적화된 알고리즘 연구가 요구된다. 본 논문에서는 최적화된 내용 기반 필터링을 활용해 사용자의 입력 패턴과 취향을 파악하여 메뉴를 추천해주는 시스템인 UBRS을 제안하고자 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.105-108
• /
• 2017

본 논문에서는 오픈마켓에서의 여행상품을 구입하기 전에 자신의 여행 기간을 입력하고 각 여행상품을 자신의 스케줄에 등록하여 개인에게 최적화된 여행 스케줄을 작성할 수 있는 시스템을 구현하였다. 그리고 개인화된 여행스케줄 생성을 위한 추천시스템은 설문형식의 사전 설정으로 개인이 선호하는 여행지를 선택하고 사용자와 유사한 성향을 지닌 기존 사용자들의 선호 콘텐츠를 추천하며, 여행상품 큐레이션 지원을 위해 현재 사용자의 상품페이지 방문패턴의 분석과 고객의 성향을 계량화한다.