資料的快速增長與變化以及分析工具日新月異，增加資料分析的挑戰，本研究希望透過一個完整機器學習流程，提供學術或企業在導入大數據分析時的參考藍圖。我們以Spark作為大數據分析的計算框架，利用MLlib的Spark.ml與Spark.mllib兩個套件建構機器學習模型，解決傳統資料分析時可能會遇到的問題。在資料分析過程中會比較Spark不同分析模組的適用性情境，首先使用本地端叢集進行開發，最後提交至Amazon雲端叢集加快建模與分析的效能。大數據資料分析流程將以微博為實驗範例，並使用香港大學新聞與傳媒研究中心提供的2012年大陸微博資料集，我們採用RDD、Spark SQL與GraphX萃取微博使用者貼文資料的特增值，並以隨機森林建構預測模型，來預測使用者是否具有官方認證的二元分類。 / The rapid growth of data volume and advanced data analytics tools dramatically increase the challenge of big data analytics services adoption. This paper presents a big data analytics pipeline referenced blueprint for academic and company when they consider importing the associated services. We propose to use Apache Spark as a big data computing framework, which Spark MLlib contains two packages Spark.ml and Spark.mllib, on building a machine learning model. This resolves the traditional data analytics problem. In this big data analytics pipeline, we address a situation for adopting suitable Spark modules. We first use local cluster to develop our data analytics project following the jobs submitted to AWS EC2 clusters to accelerate analytic performance. We demonstrate the proposed big data analytics blueprint by using 2012 Weibo datasets. Finally, we use Spark SQL and GraphX to extract information features from large amount of the Weibo users’ posts. The official certification prediction model is constructed for Weibo users through Random Forest algorithm.

桌上遊戲從休閒娛樂逐漸融入到學校教育，運用巧妙設計的遊戲機制引發學生遊玩意願，進而在愉悅中學習。數位桌遊，一個透過結合數位科技的優勢輔助學習與娛樂的概念隨著教育型桌遊而崛起；然而從產業、學習、娛樂等角度來思考，數位桌遊究竟應具何特性？其體驗是否良好？學習是否有效？透過這些問題，本研究旨在（1）瞭解桌遊產業與玩家對數位桌遊的需求，（2）設計一款體驗供需法則的數位桌遊，（3）評估數位桌遊的遊戲性與學習效益。 首先，本研究運用體驗式學習圈與建構主義等學習理論設計出桌遊《寶島建設》，接著透過訪談桌遊產業各利害關係人了解產業對數位桌遊的想像與需求，透過彙整訪談內容建立數位桌遊的設計指標，最後本研究投入研發數位桌遊與數據分析系統，用以分析學習者的學習歷程與經驗。 本研究共有32位參與者，在進行遊戲期間會採集參與者的操作行為和遊戲資料作為分析，遊戲後會填寫含有心流經驗和遊戲接受度的問卷，並接受遊戲性與學習內容相關的訪談。實驗結果顯示，參與者普遍對《寶島建設》感到滿意，從競標的數據上顯示參與者逐漸掌握資源的價格區間；所開發的數據分析系統亦能發現參與者未達表現的原因，進而對學習者提出有效建議。 總結，本研究成果為（1）透過訪談瞭解桌遊產業對數位桌遊的需求與想像。（2）設計出能體驗與學習供需法則的數位桌遊《寶島建設》，並獲得遊戲參與者們對遊戲體驗正向的回饋。（3）數據分析系統能透過歷程分析了解學習者的困難與障礙，從數據分析圖表裡也可發現學習者逐漸掌握價格區間，這顯示透過數位桌遊《寶島建設》的競標機制能有效學習掌握需求與價格的關係。 / Board games in Taiwan has risen from leisure and entertainment towards teachings in schools, by introducing fascinating game mechanism and theme to enhance student motivation makes learning more fun. Digital board games, a concept combining the advantages of digital technologies to enhance learning and entertaining arose with the rise of educational board games; however, from the aspect of industry, learning and entertainment, what characteristic should digital board game have? Does it create good experience? Is learning effective? Through these question, this research aims to (1) Understand the visions and needs of industry towards digital board game, (2) Design a digital board game to learn the law of supply & demand, (3) Evaluate the learning effectiveness and gameplay. First, the research uses the experiential cycle and constructism learning theory to design the board game Formosa Construction Ltd, then interview several industrial stakeholders to understand the needs and visions of digital board game, through the interviews concluded a design guidelines, finally the digital version of Formosa Consturction Ltd was built along with the data analysis program use to evaluate user experience and learning portfolio in game. Experiments was conducted with 32 participants, gameplay data are collected during gameplay, participants was asked to fill in a questionnaire with flow experience and acceptance, an interview session regarding gameplay and learning will be held after the questionnaire. Results indicate that participants are satisfy with the game, and data collected from auction showed that participants were progressively mastering the price range; The data analysis program was able to find reasons for participants that did not perform well, having chance to provide advice to learners. In conclusion, the research results are (1) Understand the needs and visions of digital board game through interviewing The Taiwan Board Game Industry. (2) Design Formosa Construction Ltd and obtain positive feedback. (3) The data analysis program showed the obstacles learners met through portfolio analysis, auction data analysis also showed participants was progressively mastering the price range, showing that Formosa Contruction Ltd is effective in learning the relation between needs and price.