ABSTRACT
The domination of digital technology has expanded in the field of education and it is inevitably linked to e-learning methods. Learning management systems, as an integral part of distance learning infrastructure, support a global heterogeneous student population to interact with tutors, tools and applications. Exploitation and analysis of interaction data allow colleges to understand the differences in student learning progress and provide more personalized intervention. Implementation of learning analytics and machine learning tools can accurately predict students' achievements and failures. Early prediction could lead to prompt targeted action in order to improve learning outcomes.
This work proposes a learning analytics approach using data mining and machine learning to predict the grades of the four main assignments in an annual module of Hellenic Open University. By dividing the academic year into four periods, a data analysis workflow is developed to compare several regression algorithms to accurately predict students' marks for the assignments of each period. The paper concludes in the algorithm with the highest degree of precision that determines the predictability of the main written assignments. Subsequently, a statistical measure is applied to classify the influence of models' variables. In addition, the analytical framework provides a comparison of the actual and predicted values identifying students who have included third-party services in their assignments.
- M. T. Hora, J. Bouwma-Gearhart, & H. J. Park, (2017). Data driven decision-making in the era of accountability: Fostering faculty data cultures for learning. The Review of Higher Education, 40(3), 391--426.Google ScholarCross Ref
- K. Schildkamp, L. Karbautzki, & J. Vanhoof (2014). Exploring data use practices around Europe: Identifying enablers and barriers. Studies in Educational Evaluation, 42, 15--24.Google ScholarCross Ref
- K. Daniel and B. (Ed). (2016). Big data and learning analytics in higher education: current theory and practice. Springer.Google Scholar
- J. W. You (2016). Identifying significant indicators using LMS data to predict course achievement in online learning. The Internet and Higher Education, 29, 23--30.Google ScholarCross Ref
- C. Gunn, (2014). Defining an agenda for learning analytics. In B. Hegary, J. Mc Donald & S.K. Loke (Eds), Rhetoric and Reality: Critical perspectives on educational technology, Proceedings ascilite Dudeding. pp 683--687.Google Scholar
- D. Kalles, C. Pierrakeas, & M. Xenos, (2008). Intelligently Raising Academic Performance Alerts. In 1st International Workshop on Combinations of Intelligent Methods and Applications (CIMA), 18th European Conference on Artificial Intelligence, Patras, Greece (pp. 37--42).Google Scholar
- C. Romero, M. López, J. Luna, & S. Ventura, (2013). Predicting students' final performance from participation in on-line discussion forums. Computers & Education, 68, 458--472.Google ScholarCross Ref
- E. Lotsari, V. Verykios, C. Panagiotakopoulos, & D. Kalles, (2014). A learning analytics methodology for student profiling. In Hellenic Conference on Artificial Intelligence (pp. 300--312). Springer, Cham.Google ScholarCross Ref
- C. Romero, G. Espejo, A. Zafra, & J. Romero, & S. Ventura, (2013). Web usage mining for predicting marks of students that use Moodle courses. Computer Applications in Engineering Education. {15} Ian Editor (Ed.). 2018. The title of book two (2nd. ed.). University of XXX Press, City, Chapter 100.Google Scholar
- A. Amigud, J. Arnedo-Moreno, T. Daradoumis, & A. E. Guerrero-Roldan, (2017). Using learning analytics for preserving academic integrity. The International Review of Research in Open and Distributed Learning, 18(5).Google Scholar
- Z. Papamitsiou, Z. & A. Economides, (2015). Temporal learning analytics visualizations for increasing awareness during assessment. International Journal of Educational Technology in Higher Education, 12(3), 129--147.Google Scholar
- A. F. Gkontzis, C., Karachristos, F., Lazarinis, F., Stavropoulos, & V. S. Verykios, (2017). Assessing Student Performance by Learning Analytics Dashboards. In Proceedings of the ninth International Conference in Open & Distance Learning, 9(1A).Google ScholarCross Ref
- A. Fynn, & J. Adamiak, (2018). A comparison of the utility of data mining algorithms in an open distance learning context. South African Journal of Higher Education, 32(4), 81 --95.Google ScholarCross Ref
- A. F. Gkontzis, C.V. Karachristos, C.T. Panagiotakopoulos, E. C. Stavropoulos and V. S. Verykios. (2017). "Sentiment Analysis to Track Emotion and Polarity in Student Fora". In Proceedings of the 21st Pan-Hellenic Conference on Informatics, 28--30 Sep, Larisa, Greece. ACM Google ScholarDigital Library
- A. F. Gkontzis, S. Kontsiantis, C.T. Panagiotakopoulos and V. S. Verykios (2018). Measuring Engagement to Assess Performance of Students in Distance Learning. In Proceedings of the 9th International Conference on Information, Intelligence, Systems and Applications, 23 -- 25 July Zakynthos, Greece. IEEE.Google ScholarCross Ref
- J. Bayer, H. Bydzovská, J. Géryk, T. Obsivac, & L. Popelinsky, (2012). Predicting Drop-Out from Social Behaviour of Students. International Educational Data Mining Society.Google Scholar
- M. Chen & C. Chen (2017). Detect Exam Cheating Pattern by Data Mining. Fuzzy Systems and Data Mining III: Proceedings of FSDM 2017, 299, 25.Google Scholar
- M. A., Santana, E., de Barros Costa, B. F., dos Santos Neto, I. C. L., Silva, & J. B. Rego, (2015). A predictive model for identifying students with dropout profiles in online courses. In EDM (Workshops).Google Scholar
- M. A. Hirudkar & S. S. Sherekar (2013). Comparative Analysis of Data Mining Tools and Techniques for Evaluating Performance of Database System. International Journal Of Computer Science And Applications, 6(2), 223--237.Google Scholar
- J. Demšar, T. Curk, A. Erjavec, Č. Gorup, T. Hočevar, M. Milutinovič, et al. (2013). Orange: data mining toolbox in python. Journal of Machine Learning Research. 14, 2349--2353. Google ScholarDigital Library
- T. Devasia, T. P. Vinushree, & V. Hegde, (2016). Prediction of students performance using Educational Data Mining. In International Conference on Data Mining and Advanced Computing (SAPIENCE), pp. 91 --95.Google ScholarCross Ref
- Leo Breiman (2001). Random Forests. Machine Learning. 45(1):5--32. Google ScholarDigital Library
- Yan, Xin (2009), Linear Regression Analysis: Theory and Computing, World Scientific. Google ScholarDigital Library
- Haykin, Simon (1998). Neural Networks: A Comprehensive Foundation (2 ed.). Prentice Hall. ISBN 0-13-273350-1. Google ScholarDigital Library
- Jerome H. Friedman. 2002. Stochastic gradient boosting. Comput. Stat. Data Anal. 38, 4 (February 2002), 367--378. Google ScholarDigital Library
- S.K. Shevade, S.S. Keerthi, C. Bhattacharyya, K.R.K. Murthy: Improvements to the SMO Algorithm for SVM Regression. In: IEEE Transactions on Neural Networks, 1999. Google ScholarDigital Library
- D. Aha, D. Kibler (1991). Instance-based learning algorithms. Machine Learning. 6:37--66. Google ScholarDigital Library
- S. Kotsiantis, N. Tselios, A. Filippidi & V. Komis, (2013). Using learning analytics to identify successful learners in a blended learning course, International Journal of Technology Enhanced Learning 5 (2), 133--150. Google ScholarDigital Library
- J. Demšar, (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine learning research, 7(Jan), 1 --30. Google ScholarDigital Library
- K. A. D'Souza and D. V. Siegfeldt, (2017).Empirical Research, Conceptual Framework for Detecting Cheating in Online and Take-Home Exams. Decision Sciences Journal of Innovative Education, 15 (4), 370--391.Google ScholarCross Ref
- G. Kostopoulos, S. Kotsiantis, & P. Pintelas, (2015). Predicting student performance in distance higher education using semi-supervised techniques. In Model and Data Engineering, pp. 259--270. Google ScholarDigital Library
Index Terms
- An effective LA approach to predict student achievement
Recommendations
Using Learning Analytics to Promote Student Engagement and Achievement in Blended Learning: An Empirical Study
ICEBT '18: Proceedings of the 2018 2nd International Conference on E-Education, E-Business and E-TechnologyThe emergence of blended learning has huge impact on traditional learning. Blended learning has its own unique characteristics combining the advantages of traditional learning and online learning. However, some problems of blended learning have also ...
Deploying multimodal learning analytics models to explore the impact of digital distraction and peer learning on student performance
AbstractSocial media have been extensively incorporated in higher education as an indispensable tool for learning. Nevertheless, research has conflicting findings about its effectiveness due to the highly reported digital distraction and poor ...
Highlights- Multimodal data captures course performance in blended Problem-Based Learning.
- ...
Predicting student success in a blended learning environment
LAK '20: Proceedings of the Tenth International Conference on Learning Analytics & KnowledgeBlended learning is gaining ground in contemporary education. However, studies on predictive learning analytics in the context of blended learning remain relatively scarce compared to Massive Open Online Courses (MOOCs), where such applications have ...
Comments