English  |  正體中文  |  简体中文  |  Items with full text/Total items : 49287/83828 (59%)
Visitors : 7151328      Online Users : 57
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/74297


    Title: 以自我組織映射為基礎之社會網絡建構法
    Other Titles: A self-organizing approach for social networks pre-construction
    Authors: 林子翔;Lin, Tzu-Hsiang
    Contributors: 淡江大學企業管理學系碩士班
    張瑋倫;Chang, Wei-Lun
    Keywords: 社會網絡;社會網絡分析;社會網絡建構;自我組織映射分群法;Social Network;Social Network Analysis;Social Network Construction;Self-Organization Maps
    Date: 2011
    Issue Date: 2011-12-28 18:21:30 (UTC+8)
    Abstract: 團體存在於日常生活的網絡或組織當中,團體符合了社會網絡的三個組成要素:行為者、關係以及連結;傳統社會網絡分析的方式,必頇透過問卷或是訪談等資料蒐集的方式,取得行為者間的關係與連結,藉此建構出社會網絡。過去已有許多研究針對社會網絡的形成進行探討,但皆以行為者間的關係與連結進行社會網絡的建構;本研究詴圖突破過去以行為者的關係與連結建構社會網絡的模式,設計透過個人基本資料自動化預先建構社會網絡的方法,並針對預先建構的社會網絡進行行為者中心性的分析。本研究的主要目的為:(1)在團體形成前預先自動化建構出社會網絡;(2)針對預先建構的社會網絡進行分析,找出團體中的關鍵人物;(3)以自我組織映射之非監督式分群法(SOM)為網絡分析之基礎。本研究所採用的研究對象,為淡江大學企管系大學部一到四年級的A班學生;以自動化的流程建構出網絡後,針對預先建構的網絡與實際網絡中,程度中心性、中介中心性以及接近中心性三類型的關鍵人物進行對照,檢測預先建構的網絡的準確度評估。結果顯示,其中以中介中心性在實際網絡中的相符程度最高,四個年級中介中心性的帄均準確度為89%;其次為程度中心性,四個年級程度中心性的帄均準確度為73%,且程度中心性的準確度在四個年級中的起伏程度最小,最不受到不同年級的影響;接近中心性的準確度是最低的,四個年級的接近中心性帄均準確度為70%,在四個年級的起伏程度是最大的,受到不同的四個年級的影響最大;影響預先建構的網絡與實際網絡間準確度的原因,本研究主要歸納為三項中心性本身所觀察的角度,以及以第三者判定一行為者中心性的難易程度;實際生活中外在環境的影響;以及網絡在團體發展階段中所處的階段。本研究主要貢獻在於提出以SOM分群法為基礎的社
    會網絡自動建構流程,在網絡形成前預先建構出網絡,並針對預先建構出的網絡進行三項中心性的分析,提供給管理者一個對於團體形成前以及未來發展,一個有效管理的參考模式。
    Social networks exist in our daily life in the organizations. There are three elements of social network: actors, ties (linkages) and relationships. The traditional of data collection in social network analysis uses questionnaires or interview to construct the social networks by discovering the linkages and relationships among the actors. The existing researches discussed the formation of social networks; however, they are all based on the existed linkages and relationships. This research proposes a novel way to construct social network which is merely based on personal information. Next, we conduct social network analysis via the pre-constructed social network. The purposes of this paper are: (1) pre-constructing the social network automatically before the group formation, (2). conducting the social network analysis based on the pre-constructed social network and identifying the key persons of the social network, and (3) clustering data into groups automatically based on self-organization maps (SOM). This research sampled four classes from first year to fourth year from the department of business administration of Tamkang University in Taiwan. After the pre-construction of social networks, verify key persons via three indicators (degree centrality, betweeness centrality and closeness centrality) between pre-constructed and real social networks. In addition, this work evaluates the accuracy in terms of three centralities. The result shows that the accuracy of betweenness centrality is the highest (89%). The second highest accuracy is degree centrality (73%). Furthermore, the difference of accuracy among four classes is insignificant. The accuracy of closeness centrality is the lowest (70%). Moreover, the difference of accuracy among four classes is significant. In summary, this research proposes an innovative approach which can automatically pre-construct the social network for an unknown group and verify key persons. The proposed method not only provides a different way to construct the social network but also assist managers preview the network and identify key persons proactively.
    Appears in Collections:[企業管理學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML109View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback