淡江大學機構典藏:Item 987654321/111353
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62797/95867 (66%)
Visitors : 3731940      Online Users : 532
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: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/111353


    Title: Mining evolution pattens in dynamic social networks
    Other Titles: 動態社群網路中的演化樣式探勘
    Authors: 華晟彣;Hua, Sheng-Wen
    Contributors: 淡江大學資訊工程學系碩士在職專班
    陳以錚;Chen, Yi-Cheng
    Keywords: 樣式探勘;動態社群網路;社群網路分析;Pattern Mining;Dynamic Social Network;Social Network Analysis
    Date: 2016
    Issue Date: 2017-08-24 23:50:41 (UTC+8)
    Abstract: 近年來,由於社群網站和應用程式的普及,大部分的研究都集中在結構化的社群網路分析中。現在許多的社會現象,在實際應用中,可以由社群網路中提取有意義的社交模式。然而,建立或刪除過時的用戶和關係,這通常隨著時間而演變,這樣的動態特性絕對會增加模式探勘的複雜度,過去一些研究已經提出在動態網絡的探索模式,這些研究通常將動態社群網絡處理成為一系列的關係圖,並從每個關係圖中探勘出有意義的子圖形(聚集),最後整合探勘結果成為一個序列,事實上,這些序列子圖或聚集可能不足以揭示個人的演化特徵; 以使用者的角度而言,隨著時間變化它仍然是難以觀察出與其他個體相互作用的演化。在本論文中,我們採用一個新的的表示法來表達動態社群網絡和一個新型的模式,以及演化特徵,並在一個動態社群網絡中獲取互動演化樣式。 此外,提出一個新的演算法Evolution Characteristic Miner (ECM), 有效的提昇探勘效率與維護演化特徵。ECM還採用了一些優化策略,有效地減少搜尋空間以提高性能。使用虛擬與實際資料庫的實驗結果表示ECM於動態社群網路中探勘互動演化樣式的效率,並擁有優雅的可擴展性。最後,我們應用在真實數據集ECM顯示演變特徵挖掘的實用性。
    Recently, due to the popularity of social website and APP, considerable attention has been paid to the analysis of structure in social network. Many potential social phenomena, in practice, can be extracted by discovering significant pattern in social network. Clearly, the network usually evolves with time; some new users and relationships are established, and some obsolete ones are removed. This dynamic feature definitely increases the complexity of pattern discovery. Several prior studies have proposed to discover pattern in dynamic network. These works generally treat the dynamic social network as a series of graphs and discover the significant subgraphs (clusters) from each graph, and then integrate the discovered results into a series. However, in fact, the series of subgraphs or clusters may be insufficient to reveal the evolving characteristics of individuals; in user’s point of view, it is still difficult to observe the evolution of interaction with other individuals over time. In this dissertation, we introduce a new representation to express the dynamic social network and a new type of pattern, evolution characteristic, to capture the interaction evolutions in a dynamic social network. Furthermore, a novel algorithm, Evolution Characteristic Miner (ECM), is developed to discover and maintain the evolution characteristics efficiently. ECM also employs some pruning strategies to effectively reduce the search space to improve the performance. The experimental results on synthetic and real datasets show the efficiency of ECM for extracting interaction evolution in dynamic networks, and possess graceful scalability. Finally, we apply ECM on real datasets to show the practicability of evolution characteristic mining.
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Thesis

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML146View/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