During the last decades, educational data mining has become a significant tool for the prediction of students’ progress and performance. In this work, we present a new semi-supervised self-trained two-level classification algorithm for predicting students’ graduation time. The proposed algorithm has three major features: Firstly, it identifies with high accuracy the students at-risk of not completing their studies; secondly, it classifies the students based on their expected graduation time; thirdly, it meaningfully relates the explicit classification information of labeled data with the information hidden in the unlabeled data. Our preliminary numerical experiments indicate that the proposed algorithm exhibits reliable predictions based on the students’ performance during the first two years of their studies.
CouncilNR. Building a workforce for the information economy. National Academies Press. 2001.
2.
AudSPlantyMHussarWJ. Condition of education 2011. Government Printing Office. 2011.
3.
JohnsonN. Three policies to reduce time to degree. Complete College America. 2011.
4.
StetserMCStillwellR. Public high school four-year on-time graduation rates and event dropout rates: School years 2010-11 and 2011-12. First Look. NCES 2014-391. National Center for Education Statistics. 2014.
5.
XuJMoonKH, van der SchaarM. A machine learning approach for tracking and predicting student performance in degree programs. IEEE Journal of Selected Topics in Signal Processing. 2017.
6.
LivierisIEDrakopoulouKTampakasVMikropoulosTPintelasP. Predicting secondary school students’ performance utilizing a semi-supervised learning approach. Journal of Educational Computing Research. 2018; 1-23.
7.
LivierisIEDrakopoulouKMikropoulosTTampakasVPintelasP. An ensemble-based semi-supervised approach for predicting students’ performance. in: Research on e-Learning and ICT in Education. Springer. 2018; 25-42.
8.
TamVLamEYFungSTFokWWTYuenAHK. Enhancing educational data mining techniques on online educational resources with a semi-supervised learning approach. in: 2015 IEEE International Conference on Teaching, Assessment, and Learning for Engineering. IEEE. 2015; 203-206.
9.
TrigueroIGarcíaSHerreraF. Self-labeled techniques for semi-supervised learning: Taxonomy, software and empirical study. Knowledge and Information Systems. 2015; 42(2): 245-284.
10.
ZhuXGoldbergAB. Introduction to semi-supervised learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. 2009; 3(1): 1-130.
11.
PiseNNKulkarniP. A survey of semi-supervised learning methods. in: Proceedings of the 2008 International Conference on Computational Intelligence and Security. IEEE Computer Society. 2008; 2: 30-34.
12.
ZinovevDVarutbangkulERaicuDSFurstJDArmatoIII SG. Semi-supervised learning approaches for predicting semantic characteristics of lung nodules. Intelligent Decision Technologies. 2009; 3(4): 207-217.
13.
BurgosCCampanarioMLde la PeñaDLaraJALizcanoDMartínezMA. Data mining for modeling students’ performance: A tutoring action plan to prevent academic dropout. Computers & Electrical Engineering. 2017.
14.
LivierisIEDrakopoulouKKotsilierisTTampakasVPintelasP. DSS-PSP – A Decision Support Software for Evaluating Students’ Performance. in: Engineering Applications of Neural Networks (EANN). Springer. 2017; 744: 63-74.
15.
LivierisIEKotsilierisTTampakasVPintelasP. Improving the evaluation process of students’ performance utilizing a decision support software. Neural Computing and Applications. 2018; 1-12.
16.
LivierisIETampakasVKyriakidouNMikropoulosTPintelasP. Forecasting students’ performance using an ensemble SSL algorithm. in: IEEE 1st International Conference on Technology and Innovation in Learning, Teaching and Education. 2018; 1-8.
17.
MinamiTOhuraY. Toward learning support for decision making: Utilization of library and lecture data. in: Intelligent Decision Technologies. Springer. 2012; 137-147.
18.
TourtoglouKVirvouM. An intelligent recommender system for trainers and trainees in a collaborative learning environment for UML. Intelligent Decision Technologies. 2012; 6(2): 79-95.
19.
SaaAA. Educational data mining & students’ performance prediction. International Journal of Advanced Computer Science and Applications. 2016; 7(5): 212-220.
20.
BakerRSYacefK. The state of educational data mining in 2009: A Review Future Visions. Journal of Educational Data Mining. 2009; 1(1): 3-17.
21.
ChrysafiadiKVirvouM. Student modeling approaches: A literature review for the last decade. Expert Systems with Applications. 2013; 40(11): 4715-4729.
22.
DuttAIsmailMAHerawanT. A systematic review on educational data mining. IEEE Access. 2017; 29: 103-130.
23.
Peña-AyalaA. Educational data mining: A survey and a data mining-based analysis of recent works. Expert Systems with Applications. 2014; 41(4): 1432-1462.
24.
RomeroCVenturaS. Educational data mining: A review of the state of the art. IEEE on Transactions on Systems, Man, and Cybernetics – Part C: Applications and Reviews. 2010; 40(6): 601-618.
25.
NagyHMAlyWMHegazyOF. An educational data mining system for advising higher education students. World Academy of Science, Engineering and Technology International Journal of Information Engineering. 2013; 7(10): 175-179.
26.
Iam-OnNBoongoenT. Improved student dropout prediction in thai university using ensemble of mixed-type data clusterings. International Journal of Machine Learning and Cybernetics. 2017; 8(2): 497-510.
27.
YasseinNAHelaliRGMMohomadSB. Predicting critical courses affecting students performance: A case study. Journal of Information Technology & Software Engineering. 2017; 7(5): 1-5.
28.
TampakasVLivierisIEPintelasEKaracapilidisNPintelasP. Prediction of students’ graduation time using a two-level classification algorithm. in: IEEE 1st International Conference on Technology and Innovation in Learning, Teaching and Education. 2018; 1-7.
29.
NgVCardieC. Weakly supervised natural language learning without redundant views. in: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1. Association for Computational Linguistics. 2003; 94-101.
30.
LodhiPMishraOJainS. Self-learning knowledge base using naïve Bayes classifier. Intelligent Decision Technologies. 2018; 1-8.
31.
SigdelMDinçIDinçSSigdelMSPuseyMLAygünRS. Evaluation of semi-supervised learning for classification of protein crystallization imagery. in: SOUTHEASTCON 2014. IEEE. 2014; 1-6.
32.
TrigueroISáezJALuengoJGarcíaSHerreraF. On the characterization of noise filters for self-training semi-supervised in nearest neighbor classification. Neurocomputing. 2014; 132: 30-41.
33.
YarowskyD. Unsupervised word sense disambiguation rivaling supervised methods. in: Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics. 1995; 189-196.
34.
BlumAMitchellT. Combining labeled and unlabeled data with co-training. in: 11th Annual Conference on Computational Learning Theory. ACM. 1998; 92-100.
35.
TrigueroIGarcíaSHerreraF. SEG-SSC: A framework based on synthetic examples generation for self-labeled semi-supervised classification. IEEE Transactions on Cybernetics. 2014.
36.
bin MatUBuniyaminNArsadPMKassimR. An overview of using academic analytics to predict and improve students’ achievement: A proposed proactive intelligent intervention. in: 2013 IEEE 5th Conference on Engineering Education (ICEED). IEEE. 2013; 126-130.
XuLSuenAKCY. Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Transactions on Systems, Man, and Cybernetics. 1992; 22(3): 418-435.
39.
BaumgartnerDSerpenG. Large experiment and evaluation tool for WEKA Classifiers. in: International Conference on Data Mining. 2009; 16: 340-346.
40.
HallMFrankEHolmesGPfahringerBReutemannPWittenI. The WEKA data mining software: An update. SIGKDD Explorations Newsletters. 2009; 11: 10-18.
41.
DomingosPPazzaniM. On the optimality of the simple Bayesian classifier under zero-one loss. Machine Learning. 1997; 29: 103-130.
42.
RumelhartDEHintonGEWilliamsRJ. Learning internal representations by error propagation. in: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. RumelhartDMcClellandJ, Editors. Cambridge, Massachusetts. 1986; 318-362.
43.
LernerBGutermanHAladjemMDinsteinI. A comparative study of neural network based feature extraction paradigms. Pattern Recognition Letters. 1999; 20(1): 7-14.
44.
PlattJ. Using sparseness and analytic QP to speed training of support vector machines. in: Kearns MS, Solla SA, Cohn DA, Editors. Advances in Neural Information Processing Systems. MA: MIT Press. 1999; 557-563.
QuinlanJR. C4.5: Programs for machine learning. Morgan Kaufmann, San Francisco. 1993.
47.
CohenW. Fast effective rule induction. in: International Conference on Machine Learning. 1995; 115-123.
48.
WuXKumarVQuinlanJRGhoshJYangQMotodaH, et al. Top 10 algorithms in data mining. Knowledge and Information Systems. 2008; 14(1): 1-37.
49.
WangYXuXZhaoHHuaZ. Semi-supervised learning based on nearest neighbor rule and cut edges. Knowledge-Based Systems. 2010; 23(6): 547-554.
50.
van RijsbergenCJ. Information retrieval. 2nd Ed. London: Butterworths. 1979.
51.
HodgesJLLehmannEL. Rank methods for combination of independent experiments in analysis of variance. The Annals of Mathematical Statistics. 1962; 33(2): 482-497.
52.
FinnerH. On a monotonicity problem in step-down multiple test procedures. Journal of the American Statistical Association. 1993; 88(423): 920-923.
53.
ZhouZHLiM. Tri-training: Exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering. 2005; 17(11): 1529-1541.
54.
LiMZhouZH. SETRED: Self-training with editing. in: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer. 2005; 611-621.
55.
ZhouYGoldmanS. Democratic co-learning. in: 16th IEEE International Conference on Tools with Artificial Intelligence (ICTAI). IEEE. 2004; 594-602.
56.
LiMZhouZH. Improve computer-aided diagnosis with machine learning techniques using undiagnosed samples. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans. 2007; 37(6): 1088-1098.
