| DC 欄位 |
值 |
語言 |
| DC.contributor | 資訊工程學系 | zh_TW |
| DC.creator | 黃俊堂 | zh_TW |
| DC.creator | Jyun-Tang Huang | en_US |
| dc.date.accessioned | 2016-7-13T07:39:07Z | |
| dc.date.available | 2016-7-13T07:39:07Z | |
| dc.date.issued | 2016 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=103522111 | |
| dc.contributor.department | 資訊工程學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 近年來，大規模開放式線上課程(Massive Open Online Course, MOOCs)在教育領域已逐漸成為主流趨勢，MOOCs在台灣稱為磨課師。在磨課師課程中低完課率為極需要突破的瓶頸問題，因此，有效提升完課率的機制持續受到研究學者高度關注。
相關文獻指出針對高風險學生進行介入輔導可以提升續讀率及完課率。然而，在介入輔導前需提早並精準預測高風險學生，方能針對高風險學生進行適時介入輔導。因此，本篇論文實作預警系統，提早並精準預測高風險學生，提供課程團隊預警清單。
本論文之預警系統主要根據學生進入課程時間來定義學習週次，並收集當週所有學習活動的相關資訊，達到提早並精準預測下週高風險學生的目的。實驗結果顯示，使用邏輯迴歸分析所建立下週高風險學生預測模型，其精準度達77%。 | zh_TW |
| dc.description.abstract | In recent years, Massive Open Online Courses（MOOCs）have gradually become a mainstream. However, in MOOCs, the issue of low completion rates is a big problem, developing effective mechanisms has been regarded as an important research.
According to the research, it indicated that timely intervention for at-risk students could increase retention rates and completion rates. Nevertheless, predicting for at-risk students has to be precise and in advance of interventions. In this paper, we implemented a warning system and provided a list of at-risk students for the course teams.
The predictor model uses each learners’ first learning as the first day of the week. Finally, the result shows that the precision rate of the predictive model is up to 77% | en_US |
| DC.subject | 磨課師 | zh_TW |
| DC.subject | 完課率 | zh_TW |
| DC.subject | 介入輔導 | zh_TW |
| DC.subject | 教育資料探勘 | zh_TW |
| DC.title | 透過適時介入輔導提升磨課師課程之完課率 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Increasing MOOCs completion rate with timely intervention | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |