English  |  正體中文  |  简体中文  |  Items with full text/Total items : 75533/75533 (100%)
Visitors : 27388251      Online Users : 361
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU 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://ir.lib.ncu.edu.tw/handle/987654321/67469

    Title: 大規模開放式線上課程學習行為研究-以社交媒體資料探勘為例;Learning in Massive Open Online Courses:Evidence from Social Media Mining
    Authors: 郭金鈤;Guo,Chin-Jin
    Contributors: 企業管理學系
    Keywords: MOOC;學習;資料探勘;社交媒體;情緒分析;社交網絡;MOOC;learning;social media;data mining;sentiment analysis;social networks
    Date: 2015-05-26
    Issue Date: 2015-07-30 18:55:59 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 由於許多大規模開放式線上課程(Massive Open Online Courses, MOOCs)已經運用社交媒體工具來支援大批學生,針對Twitter社交媒體進行共同知識創造及集體學習,本研究採用各種社交媒體探勘方式,分析MOOCs的推文訊息,並進一步調查相關「MOOCs學習」的各種訊息。在Twitter社交媒體上,MOOCs推文的描述性統計和趨勢分析表明,MOOCs推文中平日發佈的訊息較為活躍,是週末的5倍。在Twitter社交媒體上每月分析表明,10月份是一年中最活躍的月份,而8月是最不活躍的月份。因此,MOOCs從業人員應著重於MOOCs高峰時段訊息發佈中討論的重點,並立即對學生的回饋作出反應。此外,Twitter每月訊息活動涉及的情緒分析結果表明,輿論對整體MOOCs推文的情緒是略偏向負面,然而「MOOCs學習」推文普遍呈現較正面的信息。因此,MOOCs從業人員應調查對於MOOCs推文的負面訊息,並瞭解其背後的原因。如果當MOOCs社群中,用戶產生具體的新聞討論話題時,MOOCs從業者可以針對當日發佈的訊息進行調查,計算正面和負面推文數之間的差異,以了解公眾對新聞的看法。此外,我們針對MOOCs轉推的影響力研究表明,具影響力的用戶中前5%-10%,通常約占MOOCs正面及負面轉推訊息的50%。隨後繪製的社交網路圖可顯示出,在Twitter社交媒體訊息中MOOCs推文中,擁有最多MOOCs正面及負面推文的關鍵影響用戶是如何傳播訊息的。此外,Twitter社交網絡中MOOCs訊息通常最多可傳播到第二層的用戶。我們針對社交媒體進行訊息探勘的研究結果,認為Twitter社交媒體能夠幫助MOOCs從業者提高對MOOCs的見解,且有效地提高學生的學習。;Many massive open online courses(MOOCs)have adopted social media tools for large student audiences to co-create knowledge and engage in collective learning processes. To further understand the public opinion toward MOOCs learning, this study adopted various social media mining approaches to investigate Twitter messages. An analysis of the descriptive statistics and trends of MOOC-related Twitter messages revealed that MOOC-related discussions on Twitter were 5-fold more active on weekdays than at the weekend. A monthly analysis on Twitter showed that October was the most active month of the year, whereas August was the least active month. Therefore, MOOC practitioners should focus on MOOC discussions during peak periods to respond immediately to student feedback. In addition, the results of a sentiment analysis involving observations of monthly activities on Twitter indicated that public opinion toward MOOCs was slightly negative, although there were generally more positive messages about learning through MOOCs than there were negative ones. Therefore, MOOC practitioners should investigate negative Twitter messages related to MOOCs to understand the underlying reasons for them. When MOOCs communities discuss specific news topics, MOOC practitioners can investigate the difference between the number of positive and negative tweets on a given day to understand public opinion toward the news. Furthermore, our findings regarding the influencers of MOOCs retweets indicate that the top 5%–10% of influencers typically account for 50% of sentimental retweets about MOOCs. Social network diagrams were also developed to reveal how sentimental messages about MOOCs on Twitter were disseminated from the top influencers with the highest number of positive/negative retweets about MOOCs. The MOOCs were generally disseminated to a maximum of 2 layers of users in Twitter social networks. Our findings of social media mining show that Twitter can assist MOOC practitioners in improving their understanding of the insights of MOOCs to effectively improve student learning.
    Appears in Collections:[企業管理研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明