• 제목/요약/키워드: collaborative approach

검색결과 382건 처리시간 0.026초

A Study on the Interrelationship between the Prediction Error and the Rating's Pattern in Collaborative Filtering

  • Lee, Seok-Jun;Kim, Sun-Ok;Lee, Hee-Choon
    • Journal of the Korean Data and Information Science Society
    • /
    • 제18권3호
    • /
    • pp.659-668
    • /
    • 2007
  • Collaborative filtering approach for recommender systems are now widely applied in e-commerce to assist customers to find their needs from many that are frequently available. this approach makes recommendations for users based on the opinions to similar users in the system. But this approach is opened to users who present their preference to items or acquire the preference information form other users, noise in the system makes significant problem for accurate recommendation. In this paper, we analyze the relationship between the standard deviation of preference ratings for each user and the estimated ratings of them. The result shows that the possibility of the pre-filtering condition which detecting the factor of bad effect on the prediction of user's preference. It is expected that using this result will reduce the possibility of bad effect on recommender systems.

  • PDF

Personalized Movie Recommendation System Combining Data Mining with the k-Clique Method

  • Vilakone, Phonexay;Xinchang, Khamphaphone;Park, Doo-Soon
    • Journal of Information Processing Systems
    • /
    • 제15권5호
    • /
    • pp.1141-1155
    • /
    • 2019
  • Today, most approaches used in the recommendation system provide correct data prediction similar to the data that users need. The method that researchers are paying attention and apply as a model in the recommendation system is the communities' detection in the big social network. The outputted result of this approach is effective in improving the exactness. Therefore, in this paper, the personalized movie recommendation system that combines data mining for the k-clique method is proposed as the best exactness data to the users. The proposed approach was compared with the existing approaches like k-clique, collaborative filtering, and collaborative filtering using k-nearest neighbor. The outputted result guarantees that the proposed method gives significant exactness data compared to the existing approach. In the experiment, the MovieLens data were used as practice and test data.

분산 협력 필터링에 대한 에이전트 기반 접근 방법 (An Agent-based Approach for Distributed Collaborative Filtering)

  • 김병만;이경;;여동규
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제33권11호
    • /
    • pp.953-964
    • /
    • 2006
  • 협력 필털링은 그 유용성으로 인해 현재 학문적으로나 상업적으로 널리 사용되고 있지만 확장성 문제, 평가 데이타의 희박성 문제, 초기 평가 문제 둥을 안고 있다. 본 논문에서는 이러한 문제들을 일부 해결하기 위해 에이전트 간 협력에 기초한 분산 협력필터링 방법을 제안하였다. 제안 방법에서는 사용자의 평가정보를 에이전트가 지역 데이타베이스에 보관하고 이 정보를 친구들에게만 전파하는 방법을 사용함으로써 사용자 증가에 따른 확장성 문제를 해결하고자 하였다. 그리고 평가 데이타 부족에 따른 추천질 저하를 줄이기 위해 친구 에이전트의 의견을 반영하는 방법을 사용하였고 새로운 사용자에 대해서도 추천이 가능토록 하기 위해 사용자 프로파일을 이용한 협력필터링 방법을 사용하였다. 실험결과, 본 제안 방법이 확장성뿐만 아니라 데이타 희박성 문제 및 새로운 사용자 문제에도 도움이 됨을 확인할 수 있었다.

이러닝 시스템에서 온라인 비디오 강좌의 협업적 추천 방법 (Collaborative Recommendation of Online Video Lectures in e-Learning System)

  • 하인애;송규식;김흥남;조근식
    • 한국컴퓨터정보학회논문지
    • /
    • 제14권9호
    • /
    • pp.85-94
    • /
    • 2009
  • 온라인 비디오 강좌는 내용 파악이 힘든 컨텐츠들이 대부분이기 때문에 학습자가 원하는 정보를 찾기란 쉽지 않다. 그래서 학습자들이 필요로 하는 내용을 정확하고 빠르게 제공해 주는 서비스가 필요하게 되었다. 본 논문에서는 학습자의 요구에 맞는 비디오 강좌를 제공해주기 위해 사용자 기반의 협업적 여과 방법을 변형하여 적용하고자 한다. 제안하는 알고리즘 방법은 학습자가 평가한 선호도 정보를 바탕으로 강좌의 특성을 이용해 분할한 영역에서 학습자와 비슷한 이웃 학습자들을 찾고, 이웃 학습자들에 의해 높은 선호도를 보인 강좌를 선별하고 강좌의 속성 정보를 반영하여 학습자에게 추천해 주는 방식이다. 즉, 강좌의 특성을 고려하여 강좌별로 분할한 후사용자 기반의 협업적 여과 방법을 통해 학습자의 선호도를 예측한다. 그리고 강좌의 속성을 이용한 속성 기반의 여과 방법을 적용해 예측된 강좌들과 유사도를 비교한 후 최종적으로 학습자의 선호도와 가장 유사한 강좌를 추천해 준다.

주석을 통한 문서 기반의 공동작업 모델 (A Collaboration Model Using Annotations over Shared Documents)

  • 이은정
    • 정보처리학회논문지B
    • /
    • 제10B권2호
    • /
    • pp.205-212
    • /
    • 2003
  • 전자책 문서 기반의 공동작업 플랫폼인 ThruBook은 동기적인 공동작업 세션을 지원하는 시스템으로서 같은 전자책 파일을 사용하는 리더시스템들이 세션에 참여하여 동기적으로 액션을 공유할 수 있는 기능을 지원한다. 본 연구에서는 주석을 전자책에 부가적으로 추가될 수 있는 모든 종류의 정보로 보고, 북마크로 기억된 특정 위치나 메모, 추가적인 그림 등을 주석으로 표현하였다. 그 결과 공동작업을 위한 액션을 주석 객체로 모델링할 수 있었으며, 주석 객체의 전달을 통해 세션 참여자들이 액션을 전달받게 되는 공동작업 모델을 제안하였다. 제안된 모델은 공유 문서에 대한 공동작업 시스템에서의 공유 액션을 쉽게 모델링하는 방법론으로서 ThruBook 플랫폼은 다른 공동작업 시스템을 구축하기 위해서도 유용하게 사용될 수 있을 것으로 기대된다.

The Development and Application of International Collaborative Writing Courses on the Internet

  • Chong, LarryDwan
    • 영어어문교육
    • /
    • 제13권2호
    • /
    • pp.25-45
    • /
    • 2007
  • In this article, I discuss an International Collaborative Writing Course on the Internet (ICWCI) that focused on the learning effectiveness Korean EFL students (KEFLSs) perceived to be necessary to exchange with international EFL students (IEFLSs). The course development was based on an internet-based instructional module, applying widely accepted EFL theories for modern foreign language instruction: collaborative learning, process writing, project-based learning, and integrated approaches. Data from online discussion forum, mid-of-semester and end-of-semester surveys, and final oral interviews are conducted and discussed. KEFLSs and IEFLSs were questioned about (a) changes in attitude towards computers assisted language learning (CALL); (b) effect of computer background on motivation; (c) perception of their acquired writing skills; and (d) attitude towards collaborative learning. The result of this study demonstrated that the majority of ICWCI participants said they enjoyed the course, gained fruitful confidence in English communication and computer skills, and felt that they made significant progress in writing skills. In spite of positive benefits created by the ICWCI, it was found that there were some issues that are crucial to run appropriate networked collaborative courses. This study demonstrates that participants' computer skills, basic language proficiency, and local time differences are important factors to be considered when incorporating the ICWCI as these may affect the quality of online instructional courses and students' motivation toward network based collaboration interaction.

  • PDF

CLASSIFICATION FUNCTIONS FOR EVALUATING THE PREDICTION PERFORMANCE IN COLLABORATIVE FILTERING RECOMMENDER SYSTEM

  • Lee, Seok-Jun;Lee, Hee-Choon;Chung, Young-Jun
    • Journal of applied mathematics & informatics
    • /
    • 제28권1_2호
    • /
    • pp.439-450
    • /
    • 2010
  • In this paper, we propose a new idea to evaluate the prediction accuracy of user's preference generated by memory-based collaborative filtering algorithm before prediction process in the recommender system. Our analysis results show the possibility of a pre-evaluation before the prediction process of users' preference of item's transaction on the web. Classification functions proposed in this study generate a user's rating pattern under certain conditions. In this research, we test whether classification functions select users who have lower prediction or higher prediction performance under collaborative filtering recommendation approach. The statistical test results will be based on the differences of the prediction accuracy of each user group which are classified by classification functions using the generative probability of specific rating. The characteristics of rating patterns of classified users will also be presented.

e-Learning에서 협력학습과 학습효과에 영향을 주는 요인에 관한 연구 -상황요인, 상호작용요인, 제도요인을 중심으로 - (A Study on the Factors Facilitating the Effectiveness of Web-based Collaborative Learning - Focused on Situation, Interaction, System-)

  • 고일상;고윤정
    • Journal of Information Technology Applications and Management
    • /
    • 제13권4호
    • /
    • pp.197-214
    • /
    • 2006
  • This study explores factors to facilitate web-based collaborative learning and the effect of learning, based on the PBL(Problem Based Learning) from the constructivist approach in e-learning. A research model, using the key variables such as situations, interactions, and systems, was developed. In order to test this proposed model, experimental design and post-survey was conducted to the learners who took on-line and off-line course with team project. In the research model, situation category was divided into instructor's support, unstructured problem, and self-directed learning. Interaction category was divided into three factors; 'interaction between learners', 'interaction between learner and instructor', and 'interaction between learner and technology'. System category was divided into.monitoring and incentives. As a result, it was found that collaborative learning can be improved by situations, interactions, and systems, and the effectiveness of learning can be improved by situations and interactions in PBL.

  • PDF

협업 필터링 알고리즘에 관한 비교연구 (A Comparative Study on Collaborative Filtering Algorithm)

  • 이가베;이효맹;이현창;신성윤
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국정보통신학회 2017년도 추계학술대회
    • /
    • pp.151-153
    • /
    • 2017
  • 추천시스템 증 가장 대표적인 협업 필터링은 여러 아이템에 대한 사용자 평가 데이터를 이용하여 공통적 패턴을 찾고 특정 사용자이 대한 성호 아이템을 에상하여 추천하는 기법이다. 분 논문에서는 모두 5가지 알고리즘을 사용하였다. Recall-Precision, FPR-TPR, RMSE, MSE, MAE등 지표를 측정하였다. 실험 결과를 보면 MovieLens 데이터를 이용해 사용자에 기반 협업 필터링 알고리즘을 적용해 영화를 추천하는 것이 좋은 효과를 얻고 있다.

  • PDF

Development of a Personalized Similarity Measure using Genetic Algorithms for Collaborative Filtering

  • Lee, Soojung
    • 한국컴퓨터정보학회논문지
    • /
    • 제23권12호
    • /
    • pp.219-226
    • /
    • 2018
  • Collaborative filtering has been most popular approach to recommend items in online recommender systems. However, collaborative filtering is known to suffer from data sparsity problem. As a simple way to overcome this problem in literature, Jaccard index has been adopted to combine with the existing similarity measures. We analyze performance of such combination in various data environments. We also find optimal weights of factors in the combination using a genetic algorithm to formulate a similarity measure. Furthermore, optimal weights are searched for each user independently, in order to reflect each user's different rating behavior. Performance of the resulting personalized similarity measure is examined using two datasets with different data characteristics. It presents overall superiority to previous measures in terms of recommendation and prediction qualities regardless of the characteristics of the data environment.