• Journal of Information Technology Applications and Management
• /
• v.24 no.1
• /
• pp.169-185
• /
• 2017

This study proposes a novel recommendation algorithm that reflects the results from trust/distrust network analysis as a solution to enhance prediction accuracy of recommender systems. The recommendation algorithm of our study is based on memory-based collaborative filtering (CF), which is the most popular recommendation algorithm. But, unlike conventional CF, our proposed algorithm considers not only the correlation of the rating patterns between users, but also the results from trust/distrust relationship network analysis (e.g. who are the most trusted/distrusted users?, whom are the target user trust or distrust?) when calculating the similarity between users. To validate the performance of the proposed algorithm, we applied it to a real-world dataset that contained the trust/distrust relationships among users as well as their numeric ratings on movies. As a result, we found that the proposed algorithm outperformed the conventional CF with statistical significance. Also, we found that distrust relationship was more important than trust relationship in measuring similarities between users. This implies that we need to be more careful about negative relationship rather than positive one when tracking and managing social relationships among users.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.822-825
• /
• 2008

최근 모바일 기술의 발달로 모바일 네트워크에서 사용자들이 가지고 있는 정보를 활용하는 P2P 서비스들이 많이 연구되고 있다. 그 중에 협력적 필터링(Collaborative Filtering, CF)을 이용한 추천 서비스는 모바일 네트워크 상의 다른 사용자의 정보를 수집하여 개인화된 추천을 수행한다. 기존에 연구 된 CF 추천 시스템에서 메시지 전달을 위해 broadcasting 방식 사용되었다. broadcasting 방식은 각 모바일 기기 주위의 모든 기기로 사용자 정보를 전송함으로써 많은 트래픽을 유발시킨다. 본 논문에서는 슈퍼 피어 방식을 이용하여 메시지 전송 양을 줄여, CF를 이용한 추천 서비스를 보다 효율적으로 하고, 추천성능을 유지하게 하였다. 실험을 통해 본 논문에서 제시한 방식이 broadcasting 방식의 메시지 양을 53% 감소시켰음을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3266-3285
• /
• 2023

With the popularity of online learning, intelligent tutoring systems are starting to become mainstream for assisting online question practice. Surrounded by abundant learning resources, some students struggle to select the proper questions. Personalized question recommendation is crucial for supporting students in choosing the proper questions to improve their learning performance. However, traditional question recommendation methods (i.e., collaborative filtering (CF) and cognitive diagnosis model (CDM)) cannot meet students' needs well. The CDM-based question recommendation ignores students' requirements and similarities, resulting in inaccuracies in the recommendation. Even CF examines student similarities, it disregards their knowledge proficiency and struggles when generating questions of appropriate difficulty. To solve these issues, we first design an enhanced cognitive diagnosis process that integrates students' affection into traditional CDM by employing the non-compensatory bidimensional item response model (NCB-IRM) to enhance the representation of individual personality. Subsequently, we propose an affection-enhanced personalized question recommendation (AE-PQR) method for online learning. It introduces NCB-IRM to CF, considering both individual and common characteristics of students' responses to maintain rationality and accuracy for personalized question recommendation. Experimental results show that our proposed method improves the accuracy of diagnosed student cognition and the appropriateness of recommended questions.

• Journal of Internet Computing and Services
• /
• v.18 no.3
• /
• pp.19-28
• /
• 2017

Collaborative filtering (CF) is a system that interprets the relationship between a user and a product and recommends the product to a specific user. The CF model is advantageous in that it can recommend products to users with only rating data without any additional information such as contents. However, there are many cases where a user does not give a rating even after consuming the product as well as consuming only a small portion of the total product. This means that the number of ratings observed is very small and the user rating matrix is very sparse. The sparsity of this rating data poses a problem in raising CF performance. In this paper, we concentrate on raising the performance of latent factor model (especially SVD). We propose a new model that includes product similarity information and co occurrence information in SVD. The similarity and concurrence information obtained from the rating data increased the expressiveness of the latent space in terms of latent factors. Thus, Recall increased by 16% and Precision and NDCG increased by 8% and 7%, respectively. The proposed method of the paper will show better performance than the existing method when combined with other recommender systems in the future.

• Journal of Korea Multimedia Society
• /
• v.11 no.2
• /
• pp.257-268
• /
• 2008

Multimedia recommendation systems analyze user preferences and recommend items(multimedia contents) to a user by predicting the user's preference for those items. Among various kinds of recommendation methods, collaborative filtering(CF) has been widely used and successfully applied to practical applications. However, collaborative filtering has two inherent problems: data sparseness and the cold-start problems. If there are few known preferences for a user, it is difficult to find many similar users, and therefore the performance of recommendation is degraded. This problem is more serious when a new user is first using the system. In this paper, we propose a method of generating additional feature of users and items into CF to overcome the difficulties caused by sparseness and improve the accuracy of recommendation. In our method, we first generate additional features by using the probability distribution of feature values, then recommend items by applying collaborative filtering on the modified data to include additional features. Several experimental results that show the effectiveness of the proposed method are also presented.

• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.1-15
• /
• 2006

Currently the mobile web service is growing with a tremendous speed and mobile contents are spreading extensively. However, it is hard to search what the user wants because of some limitations of cellular phones. And the music is the most popular content, but many users experience frustrations to search their desired music. To solve these problems, this research proposes a hybrid recommendation system, MOBICORS-music (MOBIle COntents Recommender System for Music). Basically it follows the procedure of Collaborative Filtering (CF) system, but it uses Contents-Based (CB) data representation for neighborhood formation and recommendation of new music. Based on this data representation, MOBICORS-music solves the new item ramp-up problem and results better performance than existing CF systems. The procedure of MOBICORS-music is explained step by step with an illustrative example.

• Information Systems Review
• /
• v.8 no.2
• /
• pp.139-154
• /
• 2006

Recommender systems help users find their interesting items more easily or provide users with meaningful items based on their preferences. Collaborative filtering(CF) recommender systems, the most successful recommender system, use opinions of users to recommend for an active user who needs recommendation. That is, ratings which users have voted on items to indicate preference on them are the source for making recommendation. Although CF systems are designed only to use users' preferences as the source of recommendation, use of some available information is believed to increase both the performance and the accuracy of CF systems. In this paper, we propose a CF recommender system which utilizes both degree of match and demographic information(e.g., occupation, gender, age) to increase the performance and the accuracy. Since more and more information is accumulated in CF systems, it is important to reduce the data volume while maintaining the same or the higher level of accuracy. We used both degree of match and demographic information as criteria for reducing the data volume, thereby naturally enhancing the performance. It is shown that using degree of match improves the prediction accuracy too in CF systems and also that using some demographic information also results in better accuracy.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.589-592
• /
• 2005

웹을 통한 정보량의 폭발적인 증가로 인하여, 사용자에게 적합한 정보만을 제공할 수 있는 개인화 기술에 관심이 증가하고 있다. 정보를 선별하고 추천하는 대표적인 개인화 기술로서 Contentbased Filtering(CBF) 기법과 Collaborative Filtering(CF) 기법이 널리 사용되고 있다. 본 논문에서는 위에서 언급한 CBF 기법과 CF 기법을 혼합하여, 사용자 선호도를 보다 정확하게 반영할 수 있는 새로운 모델을 제시한다. 또한, Demographic Filtering 기법과 전문가의 추천을 고려한 Fusion Model 을 제시한다. 그리고 사용자 선호 모델을 실시간으로 반영하기 위한 업데이트 방법을 Exponential Smoothing 기법을 사용하여 구성하였다.

• 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.