淡江大學機構典藏:Item 987654321/74559
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62819/95882 (66%)
Visitors : 4000991      Online Users : 604
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/987654321/74559


    Title: 網路社群之情緒關懷系統
    Other Titles: An emotion attention system on social networks
    Authors: 陳育汎;Chen, Yu-Fan
    Contributors: 淡江大學資訊工程學系資訊網路與通訊碩士班
    許輝煌;Hsu, Hui-Huang
    Keywords: 社群網路;情感分析;自然語言處理;眾包;Social Network;Emotion Analysis;Natural Language Processing;Crowdsourcing
    Date: 2011
    Issue Date: 2011-12-28 18:52:50 (UTC+8)
    Abstract: 隨著Web 2.0的興起,網路社群漸漸成為人與人之間溝通的重要管道之一。在facebook塗鴉牆中,除了使用者自己可以主動留言外,還包含許多由遊戲或者是其他應用程式在使用者的塗鴉牆留言。在時間有限,但朋友許多的情況下,如何從一大群朋友之中,有效率地找出需要被關心的朋友,是件重要的事。在本論文中,系統首先過濾掉由其他程式所自動發布的留言,擷取使用者的朋友們近七日內的塗鴉牆留言,並將擷取出的留言與中文、英文、及表情符號的資料庫進行比對。其中,中文資料庫的建立是藉由眾包(crowdsourcing)的概念,我們在facebook上先製作了一個分詞遊戲,由登入該遊戲的使用者來協助進行中文字詞的情緒分類。所有蒐集的中文、英文、及表情符號在資料庫中都有對應的情緒類別。最後,系統將每篇留言的情緒量化為需要被關心的程度,每則留言與留言發布的時間結合,來給予每一位朋友需要被關懷的指標,再依照此關懷指標將朋友排序。此外,本系統也以視覺化曲線呈現每位朋友七日內的情緒波動。使用者可以直接點選分析過的節點,來直接連結對應的留言,與需要被關心的朋友互動。本系統已在facebook上開放連結使用,應用程式名稱為Friend_Smile。
    With the population of Web 2.0, online community has gradually become one of the important channels when people communicating. The wall on Facebook not only includes users’ message but also but also includes many from the games or other apps, so that how to find friends who need desire to be caring in the short time which is very important. In this paper, system filter the messages that posted by other applications, just fetching friends of user who post messages by themselves during the past 7 days and also compare the messages with database including Chinese, English, and Emoticon. The method we construct the Chinese database is the concept of “crowdsourcing”. We build a Segment-Game application on Facebook, when users login this application, they can help. All of collecting database, such as Chinese, English, and Emoticon can be belonged to a catalog. Last part, each message can be qualified and after composing each message and post time, giving an Em_value for user to take care. This system gives an attention index of each friend, and according to this value to rank. Besides, this system shows friends’ emotion changes by diagram of curves during the past seven days. If users want to care for their friends, they can click the analyzed node to interacting with their friends. The system has been published on Facebook, and named “Friend_Smile”.
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Thesis

    Files in This Item:

    File SizeFormat
    index.html0KbHTML352View/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