• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권7호
• /
• pp.1868-1887
• /
• 2024

Recommendation systems research is a subfield of information retrieval, as these systems recommend appropriate items to users during their visits. Appropriate recommendation results will help users save time searching while increasing productivity at work, travel, or shopping. The problem becomes more difficult when the items are geographical locations on the ground, as they are associated with a wealth of contextual information, such as geographical location, opening time, and sequence of related locations. Furthermore, on social networking platforms that allow users to check in or express interest when visiting a specific location, their friends receive this signal by spreading the word on that online social network. Consideration should be given to relationship data extracted from online social networking platforms, as well as their impact on the geolocation recommendation process. In this study, we compare the similarity of geographic locations based on their distance on the ground and their correlation with users who have checked in at those locations. When calculating feature embeddings for users and locations, social relationships are also considered as attention signals. The similarity value between location and correlation between users will be exploited in the overall architecture of the recommendation model, which will employ graph convolution networks to generate recommendations with high precision and recall. The proposed model is implemented and executed on popular datasets, then compared to baseline models to assess its overall effectiveness.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 추계학술대회
• /
• pp.91-94
• /
• 2011

기존의 SNS(Social Networking Service)서비스에 LBS(Location-Based Service)서비스가 부가된 LBSNS(Location-Based Social Networking Service)서비스들이 상용화되면서 큰 인기를 얻고 있다. 트위터는 그러한 서비스의 대표적인 예라고 볼 수 있다. 트위터의 현재 위치기반서비스는 자신이 원하는 지역정보와 상관없는 정보를 구독하게 하는 구조로 되어 있다. 팔로잉한 사용자는 단순히 개인적인 선호도에 의해 지역정보가 추가된 메시지를 트윗하지만 구독하는 입장의 팔로워는 자신이 원하지 않는 지역정보를 받아 볼 수도 있다. 이러한 사항을 개선하기 위해 공간조인을 이용한 필터링 기법이 제안되었다. 필터링 기법을 위한 우선적인 작업은 바로 각각의 사용자와 트윗들에 위치정보가 추가되어져야 한다. 여기서 위치정보는 MBR(Minimum Bounding Rectangle)로 표현된다. 위치정보는 동적속성 또는 정적속성으로 나누어진다. 동적인 경우를 예를 들어보면 사용자가 지속적으로 움직이는 상황을 들 수 있다. 이 때 발생되는 대량의 연속질의는 사용자가 많은 SNS의 특성상 서버에 많은 부하를 줄 수 있다. 본 논문에서는 구글 맵 상에서 Virtual Grid를 생성하여 문제를 해결 하였고 성능 평가 결과 Virtual Grid를 사용하지 않았을 때 보다 질의 발생 빈도수가 줄어들었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.109-134
• /
• 2018

Collaborative Filtering (CF) is widely used in recommendation field, which can be divided into rating-based CF and learning-to-rank based CF. Although many methods have been proposed based on these two kinds of CF, there still be room for improvement. Firstly, the data sparsity problem still remains a big challenge for CF algorithms. Secondly, the malicious rating given by some illegal users may affect the recommendation accuracy. Existing CF algorithms seldom took both of the two observations into consideration. In this paper, we propose a recommendation method based on listwise learning-to-rank by incorporating users' social information. By taking both ratings and order of items into consideration, the Plackett-Luce model is presented to find more accurate similar users. In order to alleviate the data sparsity problem, the improved matrix factorization model by integrating the influence of similar users is proposed to predict the rating. On the basis of exploring the trust relationship between users according to their social information, a listwise learning-to-rank algorithm is proposed to learn an optimal ranking model, which can output the recommendation list more consistent with the user preference. Comprehensive experiments conducted on two public real-world datasets show that our approach not only achieves high recommendation accuracy in relatively short runtime, but also is able to reduce the impact of malicious ratings.

• 한국정보통신학회논문지
• /
• 제17권2호
• /
• pp.317-322
• /
• 2013

개인정보란 살아있는 개인에 관한 정보로 성명, 주민등록번호 및 영상을 통하여 개인이 알아볼 수 있는 정보를 말한다. 기존의 방법인 하드웨어 필터를 이용한 하드웨어 형태가 아닌 웹 분산형 방식으로 웹 브라우저와 웹 서버 간의 상호 동작 방식으로 개인정보를 점검할 수 있는 방법을 제안하였다. 사용자 단에서 게시판에 작성된 글은 웹 브라우저내의 자바스크립트로 첨부된 문서를 웹 서비스단에서 문서처리기로 개인정보의 누출을 해결할 수 있는 방법을 제안하였다.

• 인터넷정보학회논문지
• /
• 제18권4호
• /
• pp.7-17
• /
• 2017

Despite various types of online social networks having different topological and functional characteristics, the kinds of online social networks considered in social recommendations are highly restricted. The pervasiveness of social networks has brought scholarly attention to expanding the scope of social recommendations into more diverse and less explored types of online social networks. As a preliminary attempt, this study examined the information-sharing patterns of a new type of online social network - unilateral (directed) network - and assessed the feasibility of the network as a useful information source. Specifically, this study mainly focused on the presence of shared interests in unilateral networks, because the shared information is the inevitable condition for utilizing the networks as a feasible source of personalized recommendations. As the results, we discovered that user pairs with direct and distant links shared significantly more similar information than the other non-connected pairs. Individual users' social properties were also significantly correlated with the degree of their information similarity with social connections. We also found the substitutability of online social networks for the top cohorts anonymously chosen by the collaborative filtering algorithm.

• 디지털산업정보학회논문지
• /
• 제11권1호
• /
• pp.47-57
• /
• 2015

Recently, Internet of Things (IoT) have become popular for research and development in many areas. IoT makes a new intelligent network between things, between things and persons, and between persons themselves. Social network service technology is in its infancy, but, it has many benefits. Adjacent users in a social network tend to trust each other more than random pairs of users in the network. In this paper, we propose recommendation technique using social network in Internet of Things environment. We study previous researches about information recommendation, IoT, and social IoT. We proposed SIoT_P(Social IoT Prediction) using social relationships and item-based collaborative filtering. Also, we proposed SR(Social Relationship) using four social relationships (Ownership Object Relationship, Co-Location Object Relationship, Social Object Relationship, Parental Object Relationship). We describe a recommendation scenario using our proposed method.

• 디지털융복합연구
• /
• 제12권8호
• /
• pp.329-335
• /
• 2014

협력 필터링은 상업적 추천 시스템에서 널리 사용되어 왔는데, 고객의 사회적 행태를 구현하여 사용자의 흥미에 부합하는 항목들을 제안하기 때문이다. 현재까지 적절한 항목을 추천하기 위한 가장 보편적인 방법은 유사한 사용자들을 찾아 그들의 평가치를 참조하는 방법이다. 본 논문은 영화를 추천하기 위해서 장르 흥미도를 기반으로 하는 새로운 유사도 공식을 제안하는데, 이는 기존 공식에서 사용자들의 평가등급 차이를 기반으로 하는 것과 대비된다. 광범위한 실험 결과에 따르면, 제안한 공식은 정확도와 추천의 질에 있어서 전통적인 유사도 공식의 성능을 크게 향상시키는 것으로 확인되었다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제59차 동계학술대회논문집 27권1호
• /
• pp.437-438
• /
• 2019

스마트폰을 중심으로 한 모바일 기기의 보급과 온라인 소셜 네트워크 서비스의 이용자들이 증가하면서 사용자들은 많은 콘텐츠를 소비하고 공유한다. 이는 콘텐츠 사용자들의 개별적 기호에 맞지 않거나 만족도가 떨어지는 콘텐츠를 소비하게 한다. 이와 같은 문제를 해결하기 위해 소셜 네트워크 사용자에게 적합한 콘텐츠를 추천하기 위한 기법에 대한 연구가 활발하게 진행되고 있다. 본 논문에서는 온라인 상에 존재하는 다양한 정보 중에서 공연과 관련한 콘텐츠들을 중심으로 사용자 성향별로 추천을 해줄 수 있는 협업필터링 방법에 대하여 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.305-318
• /
• 2022

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

• International Journal of Advanced Culture Technology
• /
• 제9권4호
• /
• pp.213-218
• /
• 2021

In order to improve the quality of social services, developed countries overseas have introduced authorization or permit system to primary filtering when entering the market that provides social services. However, in Korea, a quality evaluation system for social service quality management has been introduced and implemented, but no significant effect has been achieved so far. Therefore, the purpose of this study is to investigate the relationship between service quality, service satisfaction, and repurchase intention, which are important variables to measure social service quality improvement, and to use it for service quality management. As a result of this study, service quality, service satisfaction, and repurchase intention are important factors for service quality improvement. It is necessary to secure a service provider of and continuous user selection and service quality management are also important.