本研究旨在透過發展之學習行為微歷程記錄器蒐集網路合作式問題導向學習課程活動中學習者的學習行為微歷程，根據所蒐集資料歸納學習行為特徵分類架構，發展基於學習行為微歷程特徵建立電腦中介溝通能力預測模型的有效方法，以建立即時預測模型並檢驗預測模型正確率與穩定性。此外，也探討學習情境與學習者特質對於電腦中介溝通能力預測準確度之影響。

研究結果顯示，運用線性迴歸、樹狀迴歸演算法、序列最小優化迴歸演算法、卷積類神經網路演算法以及多層感知機演算法建立之預測模型都具有良好的預測能力，其中序列最小優化迴歸演算法建模具有最高的預測準確率與穩定性，其預測平均絕對誤差低至0.2522分。而「溝通行為」與「溝通目的」為影響電腦中介溝通能力預測模型之關鍵特徵子群，並且發展電腦中介溝通能力預測模型必須考量學習情境及活動與學習者學習行為微歷程的關係。若學習者有更多的互動討論行為、較熟悉教學活動主題、具有較多的學習者案例，都有助於建立預測成效更準確的電腦中介溝通能力預測模型。

This study aims to develop a Computer-Mediated Communication (CMC) competence forecasting model based on several considered well-known machine learning schemes and learning behavior features collected by a micro-behavior recorder from the learners while using an online collaborative problem-based learning system to perform a problem-solving learning activity. To summarize the big data generated from a huge amount of micro behaviors into the useful behavior features for constructing a good CMC competence forecasting model, this study developed the learning micro-behavior classification structure according to the collected data features and the concept of CMC. An effective method for constructing a high correctness and stableness CMC competence forecasting model was proposed and examined. In addition, the effects of learning situations and learners’ personal trait on the accuracy of CMC competence forecasting model were also discussed.

The results show that the CMC competence forecasting models developed by the linear regression algorithm, M5P algorithm, sequence minimum optimization regression algorithm, convolutional neural network algorithm and multi-layer perceptron algorithm all have good prediction performance. Among the five machine learning schemes, this study found that the sequence minimum optimization regression algorithm has the highest prediction accuracy and stability of prediction accuracy. The key features that influence the forecasting accuracy most are “communication behavior” and “communication purpose.” Moreover, the development of the forecasting model must consider the relationship between learning situations and learners’ personal trait such as discussion trait and familiar degree with the problem-solving subject because those would affect the accuracy of the developed forecasting model.

第一章 緒論 1
　第一節 研究背景與動機 1
　第二節 研究目的 4
　第三節 研究問題 4
　第四節 研究範圍與限制 5
　第五節 名詞解釋 6

第二章 文獻探討 8
　第一節 電腦中介溝通 8
　第二節 學習行為評量技術與應用 13

第三章 研究方法 19
　第一節 電腦中介溝通能力預測模型開發流程 19
　第二節 資料蒐集階段 20
　第三節 模型建立階段 34
　第四節 實驗設計 53

第四章 實驗結果與分析 59
　第一節 實驗對象敘述統計說明 59
　第二節 電腦中介溝通能力量表結果 61
　第三節 學習行為微歷程特徵資料分析 62
　第四節 特徵選取與評估 66
　第五節 電腦中介溝通能力預測模型評估與分析 69
　第六節 學習情境與學習者背景對於電腦中介溝通能力預測準確度之影響 89

第五章 結論與建議 99
　第一節 結論 99
　第二節 研究實施建議 104
　第三節 未來研究方向 107

參考文獻 109

【附錄1】參與研究同意書 119
【附錄2】學習者背景問卷 120
【附錄3】電腦中介溝通能力問卷 121

王文芳（2016）。基於序列探勘之網路科學探究學習歷程分析（碩士論文）。國立政治大學，臺北市。
王逸翔（2015）。基於腦波注意力之影音教材學習診斷系統（碩士論文）。國立臺灣師範大學，臺北市。
吳清山、林天祐（2014）。教育U辭書 U dictionary of education。臺北市：智勝文化。
宏侯政、萍崔夢（2013）。問題導向網路學習系統應用於國小五年級資訊素養與倫理之研究－著作權單元為例。教育傳播與科技研究，104，17–36。doi：10.6137/RECT.2013.104.02
林上資（2011）。數位圖書館資訊架構對數位學習之學習成效影響研究－以自然與人文數位博物館為例（碩士論文）。國立政治大學，台北市。
林佳慧（2011）。電腦化測驗系統使用效能評估之研究-以 [桃園縣國中生網路檢測系統] 為例（碩士論文）。淡江大學，新北市。
林宓（2013）。基於腦波注意力發展數位筆結合紙本學習情境之英語診斷複習系統（碩士論文）。國立臺灣師範大學，台北市。
唐士哲（2014）。重構媒介？「中介」與「媒介化」概念爬梳。新聞學研究，121，1–39。
袁梅宇（2017）。王者歸來: WEKA機器學習與大數據聖經。臺北市：佳魁資訊。
張家成（2007）。探勘合作式學習社會網路支援問題導向學習知學習伙伴推薦（碩士論文）。國立臺灣師範大學，台北市。
陳志銘（2009）。創新數位學習模式與教學應用（初版.）。臺北市：文華圖書。
陳勇汀（2017）。M5P：預測非線性連續資料的樹狀迴歸演算法。布丁布丁吃什麼？。取自：http://blog.pulipuli.info/2017/11/m5p-m5p-trees-with-linear-models-in-weka.html
曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯（2005）。資料探勘。臺北市：旗標出版社。
鄭江宇、曾瀚平（2015）。指尖下的大數據：運用Google Analytics發掘行動裝置裡的無限商機。臺北市：遠見天下文化。

Abdulkader, S. N., Atia, A., & Mostafa, M.-S. M. (2015). Brain computer interfacing: Applications and challenges. Egyptian Informatics Journal, 16(2), 213–230. DOI: 10.1016/j.eij.2015.06.002
AbuSeileek, A. F., & Qatawneh, K. (2013). Effects of synchronous and asynchronous computer-mediated communication (CMC) oral conversations on English language learners’ discourse functions. Computers & Education, 62(Supplement C), 181–190. DOI: 10.1016/j.compedu.2012.10.013
Barnes, S., & Greller, L. M. (1994). Computer‐mediated communication in the organization. Communication Education, 43(2), 129–142. DOI: 10.1080/03634529409378970
Barrows, H. S., & Tamblyn, R. M. (1980). Problem-based learning: An approach to medical education. New York, NY: Springer Publishing Company.
Blake, R. J., & Shiri, S. (2012). Online Arabic language learning: What happens after?. L2 Journal, 4(2).
Brandon. (2016, August 18). How do Convolutional Neural Networks work? Retrieved June 25, 2018, from https://brohrer.github.io/how_convolutional_neural_networks_work.html
Chen, C.-M., & Chang, C.-C. (2014). Mining learning social networks for cooperative learning with appropriate learning partners in a problem-based learning environment. Interactive Learning Environments, 22(1), 97–124. DOI: 0.1080/10494820.2011.641677
Chen, C.-M., & Huang, S.-H. (2014). Web‐based reading annotation system with an attention‐based self‐regulated learning mechanism for promoting reading performance. British Journal of Educational Technology, 45(5), 959–980. DOI: 10.1111/bjet.12119
Chesebro, J. W. (1999). Communication technologies as symbolic form: Cognitive transformations generated by the internet. Communication Quarterly, 47(3), Q8.
Chtseng. (2017, February 3). Support Vector Machines. Retrieved January 3, 2018, from https://chtseng.wordpress.com/2017/02/04/support-vector-machines/
Chua, Y. P., & Chua, Y. P. (2017). Do computer-mediated communication skill, knowledge and motivation mediate the relationships between personality traits and attitude toward Facebook? Computers in Human Behavior, 70(Supplement C), 51–59. h DOI: 10.1016/j.chb.2016.12.034
Chun, D. M. (1994). Using computer networking to facilitate the acquisition of interactive competence. System, 22(1), 17–31. DOI: 10.1016/0346-251X(94)90037-X
Couldry, N. (2015). Listening beyond the echoes: Media, ethics, and agency in an uncertain world. London, England: Routledge.
Culnan, M. J., & Markus, M. L. (1987). Information technologies. In F. M. Jablin, L. L. Putnam, K. H. Roberts, & L. W. Porter (Eds.), Handbook of organizational communication: An interdisciplinary perspective (pp. 420-443). Thousand Oaks, CA, US: Sage Publications, Inc.
Dijk, J. A. G. M. van, & Hacker, K. (2003). The digital divide as a complex and dynamic phenomenon. Information Society, 19(4), 315–326. DOI: 10.1080/01972240309487
EMBS. (2017). Biomedical Signal Processing. Retrieved January 5, 2018, from https://www.embs.org/about-biomedical-engineering/our-areas-of-research/biomedical-signal-processing/
Fang, H., Hu, Y., & Du, Z. (2015). Research on LMS Network System Architecture Based on xAPI Learning Record. China Educational Technology, 2, 65–69.
Global Pulse. (2012). Big Data for Development. Retrieved January 6, 2018, from https://www.unglobalpulse.org/sites/default/files/BigDataforDevelopment-UNGlobalPulseJune2012.pdf
Global Pulse. (2014). New Introductory Guide on Big Data for Development. Retrieved January 6, 2018, from https://www.unglobalpulse.org/bigdataprimer
Google. (2017). BigTable. Retrieved December 26, 2017, from https://cloud.google.com/bigtable/
Gu, X., Zheng, L., & Jian, J. (2014). Access to Educational Big Data:Tracking and Sharing the Learning Experience Based on the xAPI Specification. Modern Distance Education Research, 5, 13–23. DOI: 10.3969/j.issn.1009-5195.2014.05.002
Han, J., Pei, J., & Kamber, M. (2011). Data Mining: Concepts and Techniques. New York, NY: Elsevier.
Herring, S. C. (1996). Computer-mediated communication: Linguistic, social, and cross-cultural perspectives (Vol. 39). Amsterdam, Nederland: John Benjamins Publishing.
Hertz-Lazarowitz, R., & Bar-Natan, I. (2002). Writing development of Arab and Jewish students using cooperative learning (CL) and computer-mediated communication (CMC). Computers & Education, 39(1), 19–36. DOI: 10.1016/S0360-1315(02)00019-2
Hmelo-Silver, C. E. (2004). Problem-Based Learning: What and How Do Students Learn? Educational Psychology Review, 16(3), 235–266. DOI: 10.1023/B:EDPR.0000034022.16470.f3
Huang, D. (2016, September 21). SVM. Retrieved January 3, 2018, from https://taweihuang.hpd.io/2016/09/21/%e8%ae%80%e8%80%85%e6%8f%90%e5%95%8f%ef%bc%9a%e4%bb%80%e9%ba%bc%e6%98%af%e6%94%af%e6%8c%81%e5%90%91%e9%87%8f%e6%a9%9f-svm/
Kobayashi, K.、Salam, M.U.(2000)。Comparing simulated and measured values using mean squared deviation and its components。Agronomy Journal,92(2),345–352。
Kumar, S. C., Chowdary, E. D., Venkatramaphanikumar, S., & Kishore, K. V. K. (2016). M5P model tree in predicting student performance: A case study. In 2016 IEEE International Conference on Recent Trends in Electronics, Information Communication Technology (RTEICT) (pp. 1103–1107). DOI: 10.1109/RTEICT.2016.7808002
Lek, S., & Park, Y. S. (2008). Multilayer Perceptron. In S. E. Jørgensen & B. D. Fath (Eds.), Encyclopedia of Ecology (pp. 2455–2462). Oxford: Academic Press. DOI: 10.1016/B978-008045405-4.00162-2
Li, M., & Storch, N. (2017). Second language writing in the age of CMC: Affordances, multimodality, and collaboration. Journal of Second Language Writing, 36(Supplement C), 1–5. DOI: 10.1016/j.jslw.2017.05.012
Meskill, C., & Anthony, N. (2005). Foreign language learning with CMC: forms of online instructional discourse in a hybrid Russian class. System, 33(1), 89–105. DOI: 10.1016/j.system.2005.01.001
Minewiskan. (2016). Feature Selection - Microsoft. Retrieved December 26, 2017, from https://docs.microsoft.com/zh-tw/sql/analysis-services/data-mining/feature-selection-data-mining
Morae. (2017). Morae. Retrieved January 5, 2018, from https://www.techsmith.com/morae.html
Paulson, F. L., Paulson, P. R., & Meyer, C. A. (1991). What makes a portfolio a portfolio. Educational Leadership, 48(5).
Platt, J. (1998). Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines. Microsoft Research. Retrieved from https://www.microsoft.com/en-us/research/publication/sequential-minimal-optimization-a-fast-algorithm-for-training-support-vector-machines/
Quadrianto, N., & Buntine, W. L. (2017). Linear Regression. In Encyclopedia of Machine Learning and Data Mining (pp. 747–750). Boston, MA: Springer. DOI: 10.1007/978-1-4899-7687-1_481
Sammut, C., & Webb, G. I. (Eds.). (2017a). F1-Measure. In Encyclopedia of Machine Learning and Data Mining (pp. 497–497). Boston, MA: Springer. DOI: 10.1007/978-1-4899-7687-1_298
Sammut, C., & Webb, G. I. (2017b). Mean Absolute Deviation. In Encyclopedia of Machine Learning and Data Mining (pp. 805–805). Boston, MA: Springer. DOI: 10.1007/978-1-4899-7687-1_100293
Savicki, V., Kelley, M., & Lingenfelter, D. (1997). Gender, group composition, and task type in small task groups using computer-mediated communication. Computers in Human Behavior, 12(4), 549–565.
Sedgwick, P., & Greenwood, N. (2015). Understanding the Hawthorne effect. British Medical Journal, 351, h4672. DOI: 10.1136/bmj.h4672
Smith, B. (2003). The use of communication strategies in computer-mediated communication. System, 31(1), 29–53. DOI: 10.1016/S0346-251X(02)00072-6
Spitzberg, B. H. (2006). Preliminary Development of a Model and Measure of Computer-Mediated Communication (CMC) Competence. Journal of Computer-Mediated Communication, 11(2), 629–666.
Thurlow, C., Lengel, L., & Tomic, A. (2011). Computer mediated communication: social interaction and the internet. Los Angeles: SAGE.
Tin Can API. (2017). What is the Experience API?. Retrieved December 27, 2017, from https://experienceapi.com/overview/
Walther, J. B. (1994). Interpersonal Effects in Computer-Mediated Interaction: A Meta-Analysis of Social and Antisocial Communication. Communication Research, 21(4), 460–87. DOI: 10.1177/009365094021004002
Wang, Y., & Witten, I. H. (1996). Induction of model trees for predicting continuous classes (Working Paper). Retrieved from https://researchcommons.waikato.ac.nz/handle/10289/1183
Windahl, S., & McQuail, D. (1993). Communication models for the study of mass communications. London, England: Longman.
Zaccone, G. (2016). Getting Started with TensorFlow. Birmingham, England: Packt Publishing Ltd.
Zhang, X. (2017). Support Vector Machines. In Encyclopedia of Machine Learning and Data Mining (pp. 1214–1220). Springer, Boston, MA. DOI: 10.1007/978-1-4899-7687-1_810
Zweig, M. H., & Campbell, G. (1993). Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clinical Chemistry, 39(4), 561–577.