| 53 | 0 | 92 |
| 下载次数 | 被引频次 | 阅读次数 |
Virtual learning environment(VLE) MOOC provides large-scale data of resources, activities, and interactions within a course structure for predicting student performance. But it is challenging to extract and learn efficient features from student behaviors. In this paper, a three-layer ensemble learning framework for predicting student performance of online courses(TELF-PSPOC) at an early phase is proposed to analyze data collected from Open University Learning Analytics Dataset(OULAD). First, feature augmentation of student behavior is proposed to enrich current features of student performance, including pass rate and grades of all staged tests, daily clicks of online resources. Second, three-layer ensemble feature learning with heterogeneous classifiers(TEFL-HC) is proposed to benefit the integration of tree model and neural network. Compared with current two-layer ensemble learning, pretraining of features prevents overfitting while using nonlinear regression. The experiment shows that our TELF-PSPOC performs better than several baseline models. Besides, the relationship of the learning results and student behavior via VLE is further discovered.
Abstract：Virtual learning environment(VLE) MOOC provides large-scale data of resources, activities, and interactions within a course structure for predicting student performance. But it is challenging to extract and learn efficient features from student behaviors. In this paper, a three-layer ensemble learning framework for predicting student performance of online courses(TELF-PSPOC) at an early phase is proposed to analyze data collected from Open University Learning Analytics Dataset(OULAD). First, feature augmentation of student behavior is proposed to enrich current features of student performance, including pass rate and grades of all staged tests, daily clicks of online resources. Second, three-layer ensemble feature learning with heterogeneous classifiers(TEFL-HC) is proposed to benefit the integration of tree model and neural network. Compared with current two-layer ensemble learning, pretraining of features prevents overfitting while using nonlinear regression. The experiment shows that our TELF-PSPOC performs better than several baseline models. Besides, the relationship of the learning results and student behavior via VLE is further discovered.
[1]Chaichumpa S,Wicha S,Temdee P.Personalized learning in a virtual learning environment using modification of objective distance[J].Wireless Personal Communicatio ns,2021,118(3):2055-2072.
[2]Boulton C A,Kent C,Williams H T P.Virtual learning environment engagement and learning outcomes at a“bricks-and-mortar”university[J].Computers&Education,2018,126(1):129-142.
[3]Mendez O,Florez H.Applying the flipped classroom model using a vle for foreign languages learning[C]//International Conference on Applied Informatics.Colombia:Springer,2018:215-227.
[4]Abu S A,Al-Emran M,Shaalan K.Factors affecting students’performance in higher education:a systematic review of predictive data mining techniques[J].Technology,Knowledge and Learning,2019,24(4):567-598.
[5]Lacka E,Wong T C,Haddoud M Y.Can digital technologies improve students’efficiency?Exploring the role of Virtual Learning Environment and Social Media use in Higher Education[J].Computers&Education,2021,163(1):1-11.
[6]Aljohani N R,Fayoumi A,Hassan S U.Predicting atrisk students using clickstream data in the virtual learning environment[J].Sustainability,2019,11(24):1-12.
[7]Petkovic D,Sosnick-Pérez M,Okada K,et al.Using the random forest classifier to assess and predict student learning of software engineering teamwork[C]//2016 IEEE frontiers in education conference (FIE).Washington D C:IEEE,2016:1-7.
[8]Ma X,Zhou Z.Student pass rates prediction using optimized support vector machine and decision tree[C]//2018 IEEE8th annual computing and communication workshop and conference (CCWC).Washington D C:IEEE,2018:209-215.
[9]He Y,Chen R,Li X,et al.Online at-risk student identification using RNN-GRU joint neural networks[J].Information,2020,11(10):1-12.
[10]Bonafini F,Chae C,Park E,et al.How much does student engagement with videos and forums in a MOOC affect their achievement?[J].Online Learning Journal,2017,21(4):223-240.
[11]Rivas A,Gonzalez-Briones A,Hernandez G,et al.Artificial neural network analysis of the academic performance of students in virtual learning environments[J].Neurocomputing,2021,423(1):713-720.
[12]Atherton M,Shah M,Vazquez J,et al.Using learning analytics to assess student engagement and academic outcomes in open access enabling programmes[J].Open Learning:The Journal of Open,Distance and e-Learning,2017,32(2):119-136.
[13]Shehri H,Qarni A,Saati L,et al.Student performance prediction using support vector machine and k-nearest neighbor[C]//2017 IEEE 30th canadian conference on electrical and computer engineering (CCECE).Washington D C:IEEE,2017:1-4.
[14]Cardona T A.Predicting student retention using support vector machines[J].Procedia Manufacturing,2019,39(1):1827-1833.
[15]Tripathi A,Yadav S,Rajan R.Naive Bayes classification model for the student performance prediction[C]//20192nd International Conference on Intelligent Computing,Instrumentation and Control Technologies (ICICICT).Kannur:IEEE,2019:1548-1553.
[16]Apolinar-Gotardo M.Using decision tree algorithm to predict student performance[J].Indian Journal of Science and Technology,2019,12(5):1-8.
[17]Hussain M,Zhu W,Zhang W,et al.Student engagement predictions in an e-learning system and their impact on student course assessment scores[J].Computational intelligence and neuroscience,2018,2018(1):1-21.
[18]Silveira P D N,Cury D,Menezes C,et al.Analysis of classifiers in a predictive model of academic success or failure for institutional and trace data[C]//2019 IEEEFrontiers in Education Conference (FIE).Covington:IEEE,2019:1-8.
[19]Yuan T,Sun Z,Ma S.Gearbox fault prediction of wind turbines based on a stacking model and change-point detection[J].Energies,2019,12(22):1-20.
[20]Adejo O W,Connolly T.Predicting student academic performance using multi-model heterogeneous ensemble approach[J].Journal of Applied Research in Higher Education,2018,10(1):61-75.
[21]Rivas A,Chamoso P,González-Briones A,et al.Detection of cattle using drones and convolutional neural networks[J].Sensors,2018,18(7):1-15.
[22]Okubo F,Yamashita T,Shimada A,et al.A neural network approach for students’performance prediction[C]//Proceedings of the seventh international learning analytics&knowledge conference.New York:ICPS Proceedings,2017:598-599.
[23]Ranjeeth S,Latchoumi T P,Sivaram M,et al.Predicting Student Performance with ANNQ3H:A Case Study in Secondary Education[C]//2019 International Conference on Computational Intelligence and Knowledge Economy.Dubai,United Arab Emirates.IEEE,2019:603-607.
[24]Karimi H,Derr T,Huang J,et al.Online academic course performance prediction using relational graph convolutional neural network[J]//Proceedings of The 13th International Conference on Educational Data Mining.Ifrane:ERIC,2020:444-450.
[25]Phungsuk R,Viriyavejakul C,Ratanaolarn T.Development of a problem-based learning model via a virtual learning environment[J].Kasetsart Journal of Social Sciences,2017,38(3):297-306.
[26]Umair S,Sharif M M.Predicting students grades using artificial neural networks and support vector machine[M]//Encyclopedia of Information Science and Technology,Fourth Edition.Florida,USA:IGI Global,2018:5169-5182.
[27]Awad M,Ewais A.Prediction of general high school exam result level using multilayer perceptron neural networks[J].International Journal of Applied Engineering Research,2018,13(10):7621-7630.
[28]Rodríguez-Hernández C F,Musso M,Kyndt E,et al.Artificial neural networks in academic performance prediction:Systematic implementation and predictor evaluation[J].Computers and Education:Artificial Intelligence,2021,2(1):1-13.
[29]Kuzilek J,Hlosta M,Zdrahal Z.Open university learning analytics dataset[J].Scientific data,2017,4(1):1-8.
[30]Hamoud A,Hashim A S,Awadh W A.Predicting student performance in higher education institutions using decision tree analysis[J].International Journal of Interactive Multimedia and Artificial Intelligence,2018,5(2):26-31.
[31]Ma X,Sha J,Wang D,et al.Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning[J].Electronic Commerce Research and Applications,2018,31(1):24-39.
基本信息:
DOI：10.16512/j.cnki.jsjjy.2022.12.039
中图分类号:TP18;G724.82;G434
引用信息:
[1]Kun Ma,Nan Zheng,Shan Jing,等.TELF-PSPOC:Three-layer Ensemble Learning Framework for Predicting Student Performance of Online Courses[J].计算机教育,2022,No.336(12):83-93.DOI:10.16512/j.cnki.jsjjy.2022.12.039.
2022-12-10
2022-12-10
