Abstract
Predicting student performance (PSP) is of great use from an educational perspective, especially for high-risk students who need timely help to complete their studies. Previous PSP studies construct prediction models mainly on data collected from questionnaires or some specific learning systems. Instead, students’ Internet access logs were used in this study to predict high-risk students. Since the raw data in log files are high-dimensional, complex and full of noise, several methods were proposed for the preprocessing of the data source. A high-dimensional feature selection framework is then designed to prepare features for the construction of a prediction model with good trade-off between computational efficiency and prediction performance. Experiments showed that the proposed prediction model can identify about 85% of high-risk students. Some online characteristics of high-risk students were also discovered, which might help student counselors and educational researchers better understand the relationship between students’ Internet use and their academic performance.
Similar content being viewed by others
References
Abd-Alsabour N, University C, Egypt C (2014) A review on evolutionary feature selection. In: European modelling symposium. IEEE Computer Society, pp 20–26
Araque F, Roldán C, Salguero A (2009) Factors influencing university drop out rates. Comput Educ 53:563–574
Bayer J, Bydzovska H, Geryk J, Obsivac T, Popelinsky L (2012) Predicting drop-out from social behaviour of students. In: Proceedings of the 5th international conference on educational data mining, pp 103–109
Bennett S, Maton K, Kervin L (2008) The ’digital natives’ debate: a critical review of the evidence. Br J Educ Technol 39(5):775–786
Caruana R, Freitag D (1994) Greedy attribute selection. In: Proceedings of 11th international conference on machine learning. pp 28–36
Cheng CK, Paré DE, Collimore LM, Joordens S (2011) Assessing the effectiveness of a voluntary online discussion forum on improving students’ course performance. Comput Educ 56:253–261
Cocea M, Weibelzahl S (2009) Log file analysis for disengagement detection in e-learning environments. User Model User-adapt Interact 19(4):341–385
Dash M, Choi K, Scheuermann P, Liu H (2002) Feature selection for clustering-a filter solution. In: Proceedings of second international conference on data mining. pp 115–122
Dekker GW, Pechenizkiy M, Vleeshouwers JM (2009) Predicting students drop out: a case study. In: Educational data mining—Edm 2009, Cordoba, Spain, 1–3 July 2009. Proceedings of the International Conference on Educational Data Mining, pp 41–50
Eickhoff C, Teevan J, White R, Dumais S (2014) Lessons from the journey: a query log analysis of within-session learning. In: Proceedings of the seventh international conference on web search and web data mining. pp 223–232 (2014)
García-Torres M, Gómez-Vela F, Melián-Batista B, Moreno-Vega J (2016) High-dimensional feature selection via feature grouping: a variable neighborhood search approach. Inf Sci 326:102–118
Grudnitski G (1997) A forecast of achievement from student profile data. J Account Educ 15(4):549–558
Gurung B, Rutledge D (2014) Digital learners and the overlapping of their personal and educational digital engagement. Comput Educ 77:91–100
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182
Hall MA (2000) Correlation-based feature selection for discrete and numeric class machine learning. In: Proceedings of 17th international conference on machine learning. pp 359–366
Hämäläinen W, Vinni M (2011) Classifiers for educational data mining. Chapman & Hall/CRC, London
Han J, Kamber M, Pei J (2012) Data mining: concepts and techniques, 3rd edn. Morgan Kaufmann Publishers Inc, Burlington, Massachusetts
Hunley SA, Evans JH, Delgado-Hachey M, Krise J, Rich T, Schell C (2005) Adolescent computer use and academic achievement. Adolescence 40(158):307–318
Jain AK, Duin RP, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22(1):4–37
Kim Y, Street WN, Menczer F (2000) Feature selection in unsupervised learning via evolutionary search. In: Proceedings of 6th ACM SIGKDD international conference on knowledge discovery and data mining, pp 365–369
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1–2):273–324
Kotsiantis S, Patriarcheas K, Xenos M (2010) A combinational incremental ensemble of classifiers as a technique for predicting students’ performance in distance education. Knowl Based Syst 23:529–535
Kubat M, Matwin S (2000) Addressing the curse of imbalanced training sets: one-sided selection. In: International conference on machine learning, pp 179–186
Kubey RW, Lavin MJ, Barrows JR (2001) Internet use and collegiate academic performance decrements: early findings. J Commun 51(2):366–382
Liang XH (2006) The analysis about the impact of online games on college students. Sci Educ Article Collects 7:28–31 (Chinese)
Liu H, Yu L (2005) Toward integrating feature selection algorithms for classification and clustering. IEEE Trans Knowl Data Eng 17(4):491–502
Maloney E (2007) What web 2.0 can teach us about learning. Chron High Educ 53(18):B26
Marcano-edeno A, Quintanilla-Dominguez J, Andina D (2011) Breast cancer classification applying artificial metaplasticity algorithm. Neurocomputing 74(8):1243–1250
Minaei-Bidgoli B, Kashy DA, Kortemeyer G, Punch WF (2003) Predicting student performance: an application of data mining methods with an educational web-based system. In: Frontiers in education, 2003, Vol 1. FIE, pp T2A–13–18 (2003)
Mitchell A, Savill-Smith C (2004) The use of computer and video games for learning: a review of the literature. In: Fancett M (ed) Learning and skills development agency. London
Mysirlaki S, Paraskeva F (2007) Digital games: Developing the issues of socio-cognitive learning theory in an attempt to shift an entertainment gadget to an educational tool. In: Proceedings of the first IEEE international workshop on digital game and intelligent toy enhanced learning, pp 147–151
Nelder J, Wedderburn R (1995) Generalized linear models. J R Stat Soc 135(2):370–384
Ortega JL, Aguillo I (2010) Differences between web sessions according to the origin of their visits. J Informetr 4(3):331–337. doi:10.1016/j.joi.2010.02.001
Peña-Ayala A (2014) Educational data mining: a survey and a data mining-based analysis of recent works. Expert Syst Appl 41:1432–1462
Romero C, Espejo PG, Zafra A, Romero JR, Ventura S (2013) Web usage mining for predicting final marks of students that use moodle courses. Comput Appl Eng Educ 21(1):135–146. doi:10.1002/cae.20456
Romero C, Ventura S (2013) Data mining in education. WIREs Data Min Knowl Discov 3:12–27
Romero C, Ventura S, Espejo PG, Hervás C (2008) Data mining algorithms to classify students. In: Proceedings of educational data mining. pp 20–21
Romero C, Ventura S, García E (2008) Data mining in course management systems: Moodle case study and tutorial. Comput Educ 51:368–384
Sánchez RA, Cortijo V, Javed U (2014) Students perceptions of facebook for academic purposes. Comput Educ 70:138–149
Sikora M (2011) Induction and pruning of classification rules for prediction of microseismic hazards in coal mines. Expert Syst Appl 38(6):6748–6758
Thai-Nghe N, Drumond L, Krohn-Grimberghe A, Schmidt-Thieme L (2010) Recommender system for predicting student performance. Procedia Comput Sci 1(2):2811–2819
Ting SR (2001) Predicting academic success of first-year engineering students from standardized test scores and psychosocial variables. Int J Eng Educ 17(1):75–80
Usman NH, Alavi M, Shafeq SM (2014) Relationship between internet addiction and academic performance among foreign undergraduate students. Procedia Soc Behav Sci 114:845–851
Vandamme J, Meskens N, Superby J (2007) Predicting academic performance by data mining methods. Educ Econ 15(4):405–419
Xenos M (2004) Prediction and assessment of student behaviour in open and distance education in computers using bayesian networks. Comput Educ 43(4):345–359
Xue B, Zhang M, Browne WN, Yao X (2016) A survey on evolutionary computation approaches to feature selection. IEEE Trans Evolut Comput 20(4):606–626
Young KS (2004) Internet addiction: a new clinical phenomenon and its consequences. Am Behav Sci 48(4):402–415
Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. In: Proceedings of 20th international conference on machine learning, pp 856–863
Yuan XL, Li XD, Ji Y, Wang Z (2015) An empirical study on the relationship between college students’ internet use and their academic performance. Chin J ICT Educ 10:28–30 (Chinese)
Zafra A, Romero C, Ventura S (2013) Dral: a tool for discovering relevant e-activities for learners. Knowl Inf Syst 36(1):211–250
Zhou Q, Mou C, Zheng Y, Meng Y (2014) Predicting student performance from access records on general websites. In: Proceedings of the 4th international conference on electronics. Communications and Networks, Beijing (2014)
Acknowledgements
This research was supported by National Natural Science Foundation of China under Grant No. 61472464, National Natural Science Foundation Project of CQ CSTC (No. cstc2016jcyjA0276) and Fundamental Research Funds for the Central Universities (Nos. 106112016CDJSK04XK09 and 106112016CDJXY180006).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhou, Q., Quan, W., Zhong, Y. et al. Predicting high-risk students using Internet access logs. Knowl Inf Syst 55, 393–413 (2018). https://doi.org/10.1007/s10115-017-1086-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-017-1086-5