基於MOOCs之資料導向學習興趣推薦系統設計與研製

Developing a Data-Driven Learning Interest Recommendation System to Promoting Self-Paced Learning on MOOCs

張軒銘(Chang, Hsuan Ming)

指導教授 ： 黃能富

國立清華大學/電機資訊學院/資訊工程學系/碩士(2016年)

摘要

近年來大型線上開放課程 (MOOCs) 為來自世界各地數以萬計的使用這帶來學習的機會，在此同時我們能利用學生在MOOCs上產生的互動資料讓老師的教學與學生的學習更有效率。此篇論文裡，藉由學生重複觀看影片片段的習慣，我們提出了一個資料導向的學習興趣推薦系統 (Videomark)，藉由整合學生的影片觀看數據與影片字幕找出學生可能會有興趣的課程概念。
Videomark提供一個關鍵字雲做為學習興趣/難點提醒系統並希望能藉由這個方式提升學生MOOCs上的的自我調適學習。首先找出學習影片的熱門區段進一步再由影片字幕找到相對應的課程觀念給予權重，我們用這個方法為每個章節產生關鍵字雲，這個功能的讓學生快速的找到每個章節最重要的概念是非常有幫助的，對於老師而言也可以藉由這個系統了解影片中一些較困難或者講解不太清楚的部分作改進。
我們希望這個系統可以幫助在以影片為學習教材的學生複習、整合與澄清特定課程觀念，所有的想法與實作步驟會在下接下來的內容詳細的介紹。

關鍵字

大規模線上開放課程 ； 自我調適學習 ； 關鍵字雲 ； 字幕

並列摘要

The revolution of Massive Online Open Courses (MOOCs) brings great opportunities

for millions of learners worldwide. Meanwhile, student-generated data on MOOCs

could be effectively used to improve both the teaching and learning effectiveness. In

this study, considering the habit of replay the video, a data-driven learning interest rec-
ommendation system called Videomark is proposed to identify the specific concepts that

might interest leaners through integrating both the learner’s logs and video subtitles in

the Chinese-speaking environments. Videomark provide a “keywords cloud” learning

interest/difficult reminding system based on learners’ video watching logs and subtitles

which is proposed for promoting self-paced MOOC learning. By identifying the hot

video segments (via video seek event counts) and weighting the keywords of hot video

segments, we are able to establish the “keywords cloud” of each learning topic. This

feature is valuable for learners to quick identify the most important or difficult concepts

of each topic. This is also useful for the teacher to more understand which parts of the

contents of each topic are most difficult for the learners which can be further improved.

We hope that the proposed system help learners to review, consolidate, and clarify spe-
cific concepts in the video-based learning environment. The overall idea and steps will

be presented in this study

並列關鍵字

MOOCs ； self-paced learning ； keywords cloud ； subtitles

參考文獻

[7] J. Kim, P. T. Nguyen, S. Weir, P. J. Guo, R. C. Miller, and K. Z. Gajos, “Crowd- sourcing step-by-step information extraction to enhance existing how-to videos,”

[13] C. Shi, S. Fu, Q. Chen, and H. Qu, “Vismooc: Visualizing video clickstream data from massive open online courses,” in 2015 IEEE Pacific Visualization Symposium (PacificVis), April 2015, pp. 159–166.

//nodejs.org/en/, 2009.

//isocpp.org/, 1995.

//www.mongodb.com/, 2009.