本文選題：MOOC　切入點(diǎn)：學(xué)習(xí)行為數(shù)據(jù)　出處：《現(xiàn)代遠(yuǎn)程教育研究》2017年03期

【摘要】：高輟學(xué)率與低參與度是MOOC面臨的一個(gè)主要問題。根據(jù)學(xué)習(xí)結(jié)果預(yù)測(cè),及時(shí)開展有效的教學(xué)干預(yù)是改善此問題的途徑之一。當(dāng)前基于MOOC學(xué)習(xí)行為數(shù)據(jù)進(jìn)行結(jié)果預(yù)測(cè)主要以次數(shù)分析為主,較少探索其他行為指標(biāo);在預(yù)測(cè)算法上以回歸分析為主,缺少不同預(yù)測(cè)算法效果的比較分析。以ed X平臺(tái)上一門MOOC課程的學(xué)習(xí)行為數(shù)據(jù)為研究對(duì)象進(jìn)行的探索研究發(fā)現(xiàn):學(xué)習(xí)結(jié)果預(yù)測(cè)的主要參照行為指標(biāo)組合為視頻學(xué)習(xí)次數(shù)、文本學(xué)習(xí)次數(shù)、評(píng)價(jià)參與時(shí)長、評(píng)價(jià)參與次數(shù)和論壇主題發(fā)起數(shù);學(xué)習(xí)次數(shù)的預(yù)測(cè)效果要好于學(xué)習(xí)時(shí)長,并與學(xué)習(xí)時(shí)長和學(xué)習(xí)次數(shù)結(jié)合后的預(yù)測(cè)效果接近;BP神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)準(zhǔn)確率要優(yōu)于決策樹和樸素貝葉斯網(wǎng)絡(luò),且預(yù)測(cè)準(zhǔn)確率與樣本數(shù)量呈正相關(guān);而在課程學(xué)習(xí)模塊的預(yù)測(cè)比較上,評(píng)價(jià)模塊和文本模塊的學(xué)習(xí)行為數(shù)據(jù)預(yù)測(cè)率較高,互動(dòng)模塊預(yù)測(cè)率最低。研究還發(fā)現(xiàn),MOOC學(xué)習(xí)群體包含三類,分別是以視頻學(xué)習(xí)和學(xué)習(xí)評(píng)價(jià)為主、以互動(dòng)交流為輔的學(xué)習(xí)群體;以視頻學(xué)習(xí)和文本學(xué)習(xí)為主、以評(píng)價(jià)參與為輔的學(xué)習(xí)群體,以及以文本學(xué)習(xí)和學(xué)習(xí)評(píng)價(jià)為主、以互動(dòng)交流為輔的學(xué)習(xí)群體。
[Abstract]:High dropout rate and low participation are a major problem for MOOC.According to the prediction of learning results, timely and effective teaching intervention is one of the ways to improve this problem.At present, the prediction of results based on MOOC learning behavior data is mainly based on the frequency analysis, less exploration of other behavioral indicators, and the prediction algorithm based on regression analysis, the lack of comparative analysis of the results of different prediction algorithms.Taking the learning behavior data of a MOOC course on ed X platform as the research object, it is found that the main reference behavior indexes of learning result prediction are video learning times, text learning times, and the time of evaluation participation.The number of evaluations of the number of participants and the number of forum themes initiated; the prediction of the number of learning times was better than the length of the learning period,The prediction effect of the combination of learning time and learning times is close to that of decision tree and naive Bayesian network, and the prediction accuracy is positively correlated with the number of samples, and the prediction accuracy of course learning module is compared with that of course learning module, and the prediction accuracy of BP neural network is better than that of decision tree and naive Bayesian network.The prediction rate of learning behavior data is higher in evaluation module and text module, and the lowest in interactive module.The study also found that there are three kinds of learning groups: video learning and learning evaluation, interactive communication, video learning and text learning, evaluation and participation.And text learning and learning evaluation as the main, interactive communication as a supplementary learning groups.
【作者單位】： 江南大學(xué)教育信息化研究中心;北京師范大學(xué)教育技術(shù)學(xué)院;
【基金】：2014年全國教育科學(xué)“十二五”規(guī)劃教育部重點(diǎn)課題“基于教育大數(shù)據(jù)的學(xué)習(xí)分析工具設(shè)計(jì)與應(yīng)用研究”(DCA140230) 中央高�；究蒲袠I(yè)務(wù)費(fèi)專項(xiàng)資金資助課題:“‘互聯(lián)網(wǎng)+’環(huán)境下的理解性學(xué)習(xí)與認(rèn)知研究”(2017JDZD07)
【分類號(hào)】：G434

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 郝巧龍;魏振鋼;林喜軍;;MOOC學(xué)習(xí)行為分析及成績預(yù)測(cè)方法研究[J];電子技術(shù)與軟件工程;2016年07期

2 李曼麗;徐舜平;孫夢(mèng)Z，

本文編號(hào)：1705213