Multi-task MIML learning for pre-course student performance prediction

Abstract

In higher education, the initial studying period of each course plays a crucial role for students, and seriously influences the subsequent learning activities. However, given the large size of a course’s students at universities, it has become impossible for teachers to keep track of the performance of individual students. In this circumstance, an academic early warning system is desirable, which automatically detects students with difficulties in learning (i.e., at-risk students) prior to a course starting. However, previous studies are not well suited to this purpose for two reasons: 1) they have mainly concentrated on e-learning platforms, e.g., massive open online courses (MOOCs), and relied on the data about students’ online activities, which is hardly accessed in traditional teaching scenarios; and 2) they have only made performance prediction when a course is in progress or even close to the end. In this paper, for traditional classroomteaching scenarios, we investigate the task of pre-course student performance prediction, which refers to detecting at-risk students for each course before its commencement. To better represent a student sample and utilize the correlations among courses, we cast the problem as a multi-instance multi-label (MIML) problem. Besides, given the problem of data scarcity, we propose a novel multi-task learning method, i.e., MIML-Circle, to predict the performance of students from different specialties in a unified framework. Extensive experiments are conducted on five real-world datasets, and the results demonstrate the superiority of our approach over the state-of-the-art methods.

Keywords

educational data mining / academic early warning system / student performance prediction / multi-instance multi-label learning / multi-task learning

References

[1] Sweeney M, Rangwala H, Lester J, Johri A. Next-term student performance prediction: a recommender systems approach. Journal of Educational Data Mining, 2016, 8(1): 22–51

[2] Grayson A, Miller H, Clarke D D. Identifying barriers to help-seeking: a qualitative analysis of students’ preparedness to seek help from tutors. British Journal of Guidance & Counselling, 1998, 26(2): 237–253

[3] Romero C, Ventura S. Educational data mining: a review of the state of the art. IEEE Transactions on Systems Man and Cybernetics, Part C (Application and Reviews), 2010, 40(6): 601–618

[4] Qiujie L, Rachel B. The different relationships between engagement and outcomes across participant subgroups in massive open online courses. Computers & Education, 2018, 127: 41–65

[5] Ren Z, Rangwala H, Johri A. Predicting performance on MOOC assessments using multi-regression models. In: Proceedings of the 9th International Conference on Education Data Mining. 2016, 484–489

[6] Trivedi S, Pardos Z A, Heffernan N T. Clustering students to generate an ensemble to improve standard test score predictions. In: Proceedings of International Conference on Artificial Intelligence in Education. 2011, 377–384

[7] Er E. Identifying at-risk students using machine learning techniques: a case study with is 100. International Journal of Machine Learning and Computing, 2012, 2(4): 476–480

[8] Hu Y H, Lo C L, Shih S P. Developing early warning systems to predict students online learning performance. Computers in Human Behavior, 2014, 36: 469–478

[9] Macfadyen L P, Dawson S. Mining LMS data to develop an early warning system for educators: a proof of concept. Computers & Education, 2010, 54(2): 588–599

[10] Zafra A, Romero C, Ventura S. Multiple instance learning for classifying students in learning management systems. Expert Systems with Applications, 2011, 38(12): 15020–15031

[11] Kotsiantis S B, Pierrakeas C J, Pintelas P E. Preventing student dropout in distance learning using machine learning techniques. Applied Artificial Intelligence, 2004, 18(5): 411–426

[12] Xenos M. Prediction and assessment of student behaviour in open and distance education in computers using bayesian networks. Computers & Education, 2004, 43(4): 345–359

[13] Marbouti F, Diefes-Dux H A, Madhavan K. Models for early prediction of at-risk students in a course using standards-based grading. Computers & Education, 2016, 103: 1–15

[14] Meier Y, Xu J, Atan O, Schaar M V D. Predicting grades. IEEE Transactions on Signal Processing, 2016, 64(4): 959–972

[15] Gedeon T D, Turner S. Explaining student grades predicted by a neural network. In: Proceedings of International Joint Conference on Neural Networks. 2002, 609–612

[16] Acharya A, Sinha D. Early prediction of students performance using machine learning techniques. International Journal of Computer Applications, 2014, 107(1): 37–43

[17] Ma Y L, Cui C R, Nie X S, Yang G P, Shaheed K, Yin Y L. Pre-course student performance prediction with multi-instance multi-label learning. Science China Information Sciences, 2019, 62(2): 200–205

[18] Shalevshwartz S, Bendavid S. Understanding Machine Learning. 1st ed. New York: Cambridge University Press, 2014

[19] Zhou Z H, Zhang M L. Multi-instance multi-label learning with application to scene classification. In: Proceedings of the 19th International Conference on Neural Information Processing Systems. 2006, 1609–1616

[20] Zhang Y, Yang Q. A survey onmulti-task learning. 2017, arXiv preprint arXiv:1707.08114

[21] Wang A Y, Newlin M H, Tucker T L. A discourse analysis of online classroom chats: predictors of cyber-student performance. Teaching of Psychology, 2001, 28(3): 222–226

[22] Wang A Y, Newlin M H. Predictors of performance in the virtual classroom: identifying and helping at-risk cyber-students. Journal of Higher Education Academic Matters, 2002, 29(10): 21–25

[23] Essa A, Ayad H. Student success system: risk analytics and data visualization using ensembles of predictive models. In: Proceedings of International Conference on Learning Analytics and Knowledge. 2012, 158–161

[24] Lopez M I, Luna J M, Romero C, Ventura S. Classification via clustering for predicting final marks based on student participation in forums. In: Proceedings of International Conference on Educational Data Mining. 2012, 148–151

[25] Zhang M L, Zhou Z H. M3MIML: a maximum margin method for multi-instance multi-label learning. In: Proceedings of the 8th International Conference on Data Mining. 2008, 688–697

[26] Zhang M L. A k-nearest neighbor based multi-instance multi-label learning algorithm. In: Proceedings of the 22nd International Conference on Tools with Artificial Intelligence. 2010, 207–212

[27] Xu X S, Xue X, Zhou Z H. Ensemble multi-instance multi-label learning approach for video annotation task. In: Proceedings of the 19th International Conference on Multimedea. 2011, 1153–1156

[28] Li Y F, Hu J H, Jiang Y, Zhou Z H. Towards discovering what patterns trigger what labels. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence. 2012, 1012–1018

[29] Huang S J, Zhou Z H. Fast multi-instance multi-label learning. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. 2014, 1868–1874

[30] Feng J, Zhou Z H. Deep MIML network. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017, 158–161

[31] Yang Y, Wu Y F, Zhan D C, Liu Z B, Jiang Y. Complex object classification: a multi-modal multi-instance multi-label deep network with optimal transport. In: Proceedings of the 24th ACM International Conference on Knowledge Discovery and Data Mining. 2018, 2594–2603

[32] Zhou Z H, Zhang M L. Solving multi-instance problems with classifier ensemble based on constructive clustering. Knowledge & Information Systems, 2007, 11(2): 155–170

[33] Boutell M R, Luo J, Shen X, Brown C M. Learning multi-label scene classification. Pattern Recognition, 2004, 37(9): 1757–1771

[34] Zhou Z H. Ensemble Methods: Foundations and Algorithms. 1st ed. Florida: CRC Press, 2012

[35] Wang S B, Li Y F. Classifier circle method for multi-label learning. Journal of Software, 2015, 26: 2811–2819

[36] Zhou Z H. Machine Learning. 1st ed. Beijing: Tsinghua University Press, 2016

RIGHTS & PERMISSIONS

2019 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature