Multi-task MIML learning for pre-course student performance prediction
Yuling MA1,2, Chaoran CUI3(), Jun YU1, Jie GUO1, Gongping YANG1, Yilong YIN1()
1. School of Software, Shandong University, Jinan 250100, China 2. School of Information Engineering, Shandong Yingcai College, Jinan 250104, China 3. School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014, China
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.
M Sweeney, H Rangwala, J Lester, A Johri. Next-term student performance prediction: a recommender systems approach. Journal of Educational Data Mining, 2016, 8(1): 22–51
2
A Grayson, H Miller, D D Clarke. 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 https://doi.org/10.1080/03069889808259704
3
C Romero, S Ventura. 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 https://doi.org/10.1109/TSMCC.2010.2053532
4
L Qiujie, B Rachel. The different relationships between engagement and outcomes across participant subgroups in massive open online courses. Computers & Education, 2018, 127: 41–65 https://doi.org/10.1016/j.compedu.2018.08.005
5
Z Ren, H Rangwala, A Johri. Predicting performance on MOOC assessments using multi-regression models. In: Proceedings of the 9th International Conference on Education Data Mining. 2016, 484–489
6
S Trivedi, Z A Pardos, N T Heffernan. 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 https://doi.org/10.1007/978-3-642-21869-9_49
7
E Er. 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 https://doi.org/10.7763/IJMLC.2012.V2.171
8
Y H Hu, C L Lo, S P Shih. Developing early warning systems to predict students online learning performance. Computers in Human Behavior, 2014, 36: 469–478 https://doi.org/10.1016/j.chb.2014.04.002
9
L P Macfadyen, S Dawson. Mining LMS data to develop an early warning system for educators: a proof of concept. Computers & Education, 2010, 54(2): 588–599 https://doi.org/10.1016/j.compedu.2009.09.008
10
A Zafra, C Romero, S Ventura. Multiple instance learning for classifying students in learning management systems. Expert Systems with Applications, 2011, 38(12): 15020–15031 https://doi.org/10.1016/j.eswa.2011.05.044
11
S B Kotsiantis, C J Pierrakeas, P E Pintelas. Preventing student dropout in distance learning using machine learning techniques. Applied Artificial Intelligence, 2004, 18(5): 411–426 https://doi.org/10.1080/08839510490442058
12
M Xenos. Prediction and assessment of student behaviour in open and distance education in computers using bayesian networks. Computers & Education, 2004, 43(4): 345–359 https://doi.org/10.1016/j.compedu.2003.09.005
13
F Marbouti, H A Diefes-Dux, K Madhavan. Models for early prediction of at-risk students in a course using standards-based grading. Computers & Education, 2016, 103: 1–15 https://doi.org/10.1016/j.compedu.2016.09.005
T D Gedeon, S Turner. Explaining student grades predicted by a neural network. In: Proceedings of International Joint Conference on Neural Networks. 2002, 609–612
16
A Acharya, D Sinha. Early prediction of students performance using machine learning techniques. International Journal of Computer Applications, 2014, 107(1): 37–43 https://doi.org/10.5120/18717-9939
17
Y L Ma, C R Cui, X S Nie, G P Yang, K Shaheed, Y L Yin. Pre-course student performance prediction with multi-instance multi-label learning. Science China Information Sciences, 2019, 62(2): 200–205 https://doi.org/10.1007/s11432-017-9371-y
18
S Shalevshwartz, S Bendavid. Understanding Machine Learning. 1st ed. New York: Cambridge University Press, 2014
19
Z H Zhou, M L Zhang. 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
Y Zhang, Q Yang. A survey onmulti-task learning. 2017, arXiv preprint arXiv:1707.08114
21
A Y Wang, M H Newlin, T L Tucker. A discourse analysis of online classroom chats: predictors of cyber-student performance. Teaching of Psychology, 2001, 28(3): 222–226 https://doi.org/10.1207/S15328023TOP2803_09
22
A Y Wang, M H Newlin. 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
A Essa, H Ayad. 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 https://doi.org/10.1145/2330601.2330641
24
M I Lopez, J M Luna, C Romero, S Ventura. 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
M L Zhang, Z H Zhou. M3MIML: a maximum margin method for multi-instance multi-label learning. In: Proceedings of the 8th International Conference on Data Mining. 2008, 688–697 https://doi.org/10.1109/ICDM.2008.27
26
M L Zhang. 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 https://doi.org/10.1109/ICTAI.2010.102
27
X S Xu, X Xue, Z H Zhou. Ensemble multi-instance multi-label learning approach for video annotation task. In: Proceedings of the 19th International Conference on Multimedea. 2011, 1153–1156 https://doi.org/10.1145/2072298.2071962
28
Y F Li, J H Hu, Y Jiang, Z H Zhou. Towards discovering what patterns trigger what labels. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence. 2012, 1012–1018
29
S J Huang, Z H Zhou. Fast multi-instance multi-label learning. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. 2014, 1868–1874
30
J Feng, Z H Zhou. Deep MIML network. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017, 158–161
31
Y Yang, Y F Wu, D C Zhan, Z B Liu, Y Jiang. 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 https://doi.org/10.1145/3219819.3220012
32
Z H Zhou, M L Zhang. Solving multi-instance problems with classifier ensemble based on constructive clustering. Knowledge & Information Systems, 2007, 11(2): 155–170 https://doi.org/10.1007/s10115-006-0029-3
