• Title/Summary/Keyword: Social Network Analysis(sna)

Search Result 180, Processing Time 0.025 seconds

Resolving the 'Gray sheep' Problem Using Social Network Analysis (SNA) in Collaborative Filtering (CF) Recommender Systems (소셜 네트워크 분석 기법을 활용한 협업필터링의 특이취향 사용자(Gray Sheep) 문제 해결)

  • Kim, Minsung;Im, Il
    • Journal of Intelligence and Information Systems
    • /
    • v.20 no.2
    • /
    • pp.137-148
    • /
    • 2014
  • Recommender system has become one of the most important technologies in e-commerce in these days. The ultimate reason to shop online, for many consumers, is to reduce the efforts for information search and purchase. Recommender system is a key technology to serve these needs. Many of the past studies about recommender systems have been devoted to developing and improving recommendation algorithms and collaborative filtering (CF) is known to be the most successful one. Despite its success, however, CF has several shortcomings such as cold-start, sparsity, gray sheep problems. In order to be able to generate recommendations, ordinary CF algorithms require evaluations or preference information directly from users. For new users who do not have any evaluations or preference information, therefore, CF cannot come up with recommendations (Cold-star problem). As the numbers of products and customers increase, the scale of the data increases exponentially and most of the data cells are empty. This sparse dataset makes computation for recommendation extremely hard (Sparsity problem). Since CF is based on the assumption that there are groups of users sharing common preferences or tastes, CF becomes inaccurate if there are many users with rare and unique tastes (Gray sheep problem). This study proposes a new algorithm that utilizes Social Network Analysis (SNA) techniques to resolve the gray sheep problem. We utilize 'degree centrality' in SNA to identify users with unique preferences (gray sheep). Degree centrality in SNA refers to the number of direct links to and from a node. In a network of users who are connected through common preferences or tastes, those with unique tastes have fewer links to other users (nodes) and they are isolated from other users. Therefore, gray sheep can be identified by calculating degree centrality of each node. We divide the dataset into two, gray sheep and others, based on the degree centrality of the users. Then, different similarity measures and recommendation methods are applied to these two datasets. More detail algorithm is as follows: Step 1: Convert the initial data which is a two-mode network (user to item) into an one-mode network (user to user). Step 2: Calculate degree centrality of each node and separate those nodes having degree centrality values lower than the pre-set threshold. The threshold value is determined by simulations such that the accuracy of CF for the remaining dataset is maximized. Step 3: Ordinary CF algorithm is applied to the remaining dataset. Step 4: Since the separated dataset consist of users with unique tastes, an ordinary CF algorithm cannot generate recommendations for them. A 'popular item' method is used to generate recommendations for these users. The F measures of the two datasets are weighted by the numbers of nodes and summed to be used as the final performance metric. In order to test performance improvement by this new algorithm, an empirical study was conducted using a publically available dataset - the MovieLens data by GroupLens research team. We used 100,000 evaluations by 943 users on 1,682 movies. The proposed algorithm was compared with an ordinary CF algorithm utilizing 'Best-N-neighbors' and 'Cosine' similarity method. The empirical results show that F measure was improved about 11% on average when the proposed algorithm was used

    . Past studies to improve CF performance typically used additional information other than users' evaluations such as demographic data. Some studies applied SNA techniques as a new similarity metric. This study is novel in that it used SNA to separate dataset. This study shows that performance of CF can be improved, without any additional information, when SNA techniques are used as proposed. This study has several theoretical and practical implications. This study empirically shows that the characteristics of dataset can affect the performance of CF recommender systems. This helps researchers understand factors affecting performance of CF. This study also opens a door for future studies in the area of applying SNA to CF to analyze characteristics of dataset. In practice, this study provides guidelines to improve performance of CF recommender systems with a simple modification.

  • A Study on the regional cluster of munition industry by Social Network Analysis (사회연결망분석을 통한 군수품 산업의 지역별 클러스터 관계에 관한 연구)

    • Park, Dongsoo;Kim, JeongHwan;Lee, Donghun
      • Journal of the Korea Academia-Industrial cooperation Society
      • /
      • v.19 no.10
      • /
      • pp.386-393
      • /
      • 2018
    • The Korean military supplies industry tends to become limited in terms of its development to specific areas in line with strategic promotion policies of the local private direct industrial site. However, the relation between base and small cluster is getting lower of the local industrial site. In this study, information related to authorized test reports for munitions was collected through the military quality information system and subjected to social network analysis(SNA). SNA was performed through the relationships among defense quality assurance agencies, test institutions, contracts and cooperative firms through UCINET's Two-Mode Network. In the field of weapon systems, the median technology industry, and the test analysis dependent are high in Seoul, so the analysis revealed that strengthening the infrastructure for test analysis is needed. Also, it was deemed necessary for government-driven political support. Besides, the field support system was efficiently utilizing a relatively local test analysis. It was analyzed that they are overcoming the regional boundaries of small clusters by strategically changing their contract and cooperative firms' status. The research found some spatial inconsistencies between base and small clusters in the military supplies industry, and it was judged that a political suggestion was needed.

    A Study on the Vulnerability Assessment Model for National Defense Intelligence System Using SNA (사회연결망분석 개념을 적용한 국방정보체계 취약점 분석·평가 모형 연구)

    • Jang, Youngcheon;Kang, Kyongran;Choi, Bongwan
      • Journal of the Korea Institute of Military Science and Technology
      • /
      • v.20 no.3
      • /
      • pp.421-430
      • /
      • 2017
    • In this research, we propose a methodology for assessing security vulnerability of the national defense intelligence system, considering not only target elements but also the interconnection relationship of the whole system. Existing approaches decide the security vulnerability of the whole system by assessing only target elements. However, those approaches have an issue with potentially showing the same outcome for the systems that have identical target elements but the different types of interconnection relationships. We propose a more practical assessment method which takes the interconnection relationship of a whole system into consideration based on the concept of SNA(Social Network Analysis).

    Deducting Core Parts of ROK Naval Ship's Engine Based on SNA (SNA 기반의 해군 추진엔진 예방정비 요소 도출)

    • Yoo, Jung-Min;Yoon, Soung-Woong;Lee, Sang-Hoon
      • Proceedings of the Korean Society of Computer Information Conference
      • /
      • 2019.01a
      • /
      • pp.419-422
      • /
      • 2019
    • 해군은 계획된 함정 수리기간을 통해 성능 유지를 위한 장비 정비를 수행한다. 함정의 수리기간이 한정되어있고, 장비는 많은 정비 대상 구성품으로 이루어져 통상의 경우 성능이 저하된 구성품을 미리 선정하여 일부분에 대해서만 정비가 수행된다. 본 연구에서는 SNA 분석을 통해 함정 수리 시 정비 대상 구성품을 더욱 효과적으로 선정할 수 있도록, 집중적으로 정비가 수행된 개체를 확인하고 이를 예방정비를 위한 정비요소로 도출하고자 하였다. 이를 위해 특정 모델을 샘플로, 도입시부터 ${\bigcirc}{\bigcirc}{\bigcirc}{\bigcirc}$년까지의 정비데이터를 수집하여 분석을 진행하였다.

    • PDF

    Monitoring social networks based on transformation into categorical data

    • Lee, Joo Weon;Lee, Jaeheon
      • Communications for Statistical Applications and Methods
      • /
      • v.29 no.4
      • /
      • pp.487-498
      • /
      • 2022
    • Social network analysis (SNA) techniques have recently been developed to monitor and detect abnormal behaviors in social networks. As a useful tool for process monitoring, control charts are also useful for network monitoring. In this paper, the degree and closeness centrality measures, in which each has global and local perspectives, respectively, are applied to an exponentially weighted moving average (EWMA) chart and a multinomial cumulative sum (CUSUM) chart for monitoring undirected weighted networks. In general, EWMA charts monitor only one variable in a single chart, whereas multinomial CUSUM charts can monitor a categorical variable, in which several variables are transformed through classification rules, in a single chart. To monitor both degree centrality and closeness centrality simultaneously, we categorize them based on the average of each measure and then apply to the multinomial CUSUM chart. In this case, the global and local attributes of the network can be monitored simultaneously with a single chart. We also evaluate the performance of the proposed procedure through a simulation study.

    Network Analysis to Describe Service Link for Customized Visiting Health Care Program (맞춤형방문건강관리사업의 지역사회 네트워크 탐색)

    • Jang, Soong-Nang;Cho, Sung-Il
      • Korean Journal of Health Education and Promotion
      • /
      • v.29 no.1
      • /
      • pp.1-11
      • /
      • 2012
    • Objectives: The nurse visiting health service named Customized Visiting Health Care Program(CVHCP) requires the service innovations incorporating community support into a local service network. The purpose of this study was to assess the community network in CVHCP and inform improvement in this network. Methods: We used Social Network Analysis(SNA) in one CVHCP at H city. Network links were generated by self-administered questionnaires by the 14 community resource centers who quantified their links to all other 25 agents on the list. Links were analyzed by a dichotomous scale for any experience of collaboration and a scored scale of 0 to 3 for level of collaboration using UCINET v6. Results: A list of 14 agents was generated, and local network was dominated by the Public Health Center and a local welfare center named Unlimited Care Center(UCC). According to centrality score, UCC was the most prominent agent, and Public Health Center was the most influential agent, being a link in the pathway flow between other agents for 9.5% of contribution. CVHCP scored lower rank of prominent with 30.8% of other agents reported referring to it. Conclusions: Social network analysis provides a useful network description for informing and evaluation service network improvement in maximizing its service for the CVHCP.

    A Study on Contents and Trends of Fisheries Management Research with Social Network Analysis (사회네트워크 분석을 이용한 수산경영학 관련 연구의 추세와 내용분석)

    • Lee, Dong-Ho
      • The Journal of Fisheries Business Administration
      • /
      • v.48 no.4
      • /
      • pp.27-43
      • /
      • 2017
    • The major purpose of this study is to find and analyze the characteristics of Fisheries Business Administration Research based on using social network analysis. This study examines every paper of The Journal of Fisheries Business Administration from 2007 to 2016. This study analyzes fisheries business administration research through bibliometric data including research trends, researcher characteristics, and key words. The 229 source articles are all papers published from 2007 to 2016 in The Journal of Fisheries Business Administration in Korea. Comparing with previous research, the major research areas of Korean fisheries business administration have a little changed and the topics of recent research are much diversified. Through basically based on frequency analysis and SNA(Social Network Analysis) method, most of the bibliographical characteristics were founded. And based on the result of this study showed that 1) increasement on number of researcher and organization 2) climate change and economic related topics are most popular terms 3) DEA is most adopted methodology in recent papers 4) joint research among the organizations has somewhat been increased 5) human resource management, history of fisheries management and education still have been conducted in terms of sustainability.

    A Study on the Evaluation of Coastal Shipping's Centrality Using a Social Network Analysis (SNA를 활용한 연안해운 중심성 평가에 관한 연구)

    • LEE, Hae-Chan;Park, Sung-Hoon;Yeo, Gi-Tae
      • Journal of Digital Convergence
      • /
      • v.19 no.2
      • /
      • pp.69-81
      • /
      • 2021
    • Coastal shipping performs a pivotal role as a national transportation network and is highly valuable in terms of enabling more economical transportation at affordable prices than road transportation. In this regard, this study aimed to examine changes in the characteristics and centrality of South Korea's costal shipping sea-route networks by analyzing the centrality of domestic coastal shipping. To this end, social network analysis was used as an analysis technique that enables an analysis on the characteristics of coastal shipping networks. As a result, Jeollanam-do showed the highest degree centrality, ranking first in both the in-degree and the out-degree. Jeollanam-do also exhibited the highest betweenness centrality, and Gangwon-do registered the highest closeness centrality. In terms of hub and authority centrality, Jeollanam-do topped the list, followed by Gyeongsangnam-do and Gangwon-do in order. Lastly, Jeollanam-do ranked highest in the hub index, followed by Incheon, other regions, and Gangwon-do in order. This study is significant for suggesting the cities and provinces that play a key role in coastal shipping each year and their corresponding items. Future studies are recommended to identify the trend of coastal shipping through more detailed research on each port by city and province.

    Co-author Network Characteristics of Korean System Dynamics Review (한국시스템다이내믹스 학회지 공저자 네트워크 특성에 관한 연구)

    • Kim, Sun-Duck;Sin, Cheol;Jung, Hyung-Ki;Lee, Man-Hyung
      • Korean System Dynamics Review
      • /
      • v.17 no.3
      • /
      • pp.31-50
      • /
      • 2016
    • This study examines the basic conditions of joint authorship research activities in the Korean System Dynamics Review and points out the structural co-author network characteristics among co-authored papers based on the social network analysis(SNA) techniques. In specific, this study identifies the cooperative relationship of research papers in the Korean System Dynamics Review, knowledge formation, and knowledge propagation paths. The study results imply that Korean System Dynamics Review has exhibited the typical 'Steven's power law,' which is repeatedly observed among complex systems, and that knowledge structure centered upon and propagated around couples of researchers. Additionally, the study results present that there have been active personal exchanges among major researchers. In contrast, personal contacts among research groups and within groups seem relatively weak.

    An Empirical Study on the Sub-factors of Middle School Character Education using Social Network Analysis (사회 네트워크 분석을 이용한 중등 인성 교육의 세부요인에 관한 실증 연구)

    • Kim, Hyojung
      • Journal of Korea Society of Digital Industry and Information Management
      • /
      • v.13 no.2
      • /
      • pp.87-98
      • /
      • 2017
    • The advancements in scientific technology and information network in the 21st century allow us to easily acquire a desired knowledge. In the midst of today's informatization, globalization, and cultural diversification, adolescents experience emotional confusion while accommodating diverse cultures and information. This study aimed at examining three aspects of character suggested by the Ministry of Education, which are ethics, sociality, and emotion, and the actual sub-factors required for character education. To that end, a survey was conducted with adolescents who were at a character-building age, and social network analysis (SNA) was performed to determine the effect of character education on the sub-factors. The statistics program SPSS was used to investigate the general traits of the subjects and the validity of the research variables. The 2-mode data that were finally selected were converted to 2-mode data using NetMinder 4, which is a network analysis tool. Furthermore, a data network was established based on a quasi-network that represents the relationships between ethics, sociality, and emotion. The results of this study showed that the subjects considered honesty and justice to be the sub-domains of the ethics domain. In addition, they identified sympathy, communication, consideration for others, and cooperation as the sub-domains of the sociality domain. Finally, they believed that self-understanding and self-control were the sub-domains of the emotion domain.


    (34141) Korea Institute of Science and Technology Information, 245, Daehak-ro, Yuseong-gu, Daejeon
    Copyright (C) KISTI. All Rights Reserved.