Application of Machine Learning Algorithms in Analysis of Learners’ Behaviour Data

International Journal of Computer Science and Engineering

© 2019 by SSRG - IJCSE Journal

Volume 6 Issue 10

Year of Publication : 2019

Authors : Jinjin Liang, Yong Nie

10.14445/23488387/IJCSE-V6I10P103

How to Cite?

Jinjin Liang, Yong Nie, "Application of Machine Learning Algorithms in Analysis of Learners’ Behaviour Data," SSRG International Journal of Computer Science and Engineering , vol. 6,  no. 10, pp. 13-17, 2019. Crossref, https://doi.org/10.14445/23488387/IJCSE-V6I10P103

Abstract:

Education Informatization is conducive to obtaining the Learners’ behaviour data both from the offline traditional classroom by the educators and the network classroom by the online platform. If machine learning algorithms can be designed to reveal the information underneath these behaviour data, it will provide scientific evidences for educators to make wise decisions and design effective teaching strategies. A framework is constructed for applying machine learning algorithms into the Learners’ behaviour data, which includes analysing learners’ characteristics by Clustering algorithm, constructing a risk assessment model by Support Vector Machine (SVM) and designing an outlier detection model by Support Vector Data Description (SVDD). Utilizing the results derived from those algorithms, the educators can design effective teaching process to match the learners’ practical situation, carry out the teaching interventions. Machine learning algorithms provide theoretical foundation for the realization of learner-cantered, individualized, precise and intelligent teaching process.

Keywords:

Education Informatization, Learners’ behaviour data, Machine learning algorithms, Analysing learners’ characteristics, Risk assessment, Outlier detection

References:

[1] Mittag, H. J. . Blended Learning in Practice: An overview on Recent Developments [J]. Journal of Lifelong Learning Society, 2016, 1(5): 171-186.
[2] Chen, H. J., Dai, Y. H., & Feng, Y. J. et al. Construction of Affective Education in Mobile Learning: The study Based on Learner’s Interest and Emotion Recognition [J]. Computer Science & Information Systems, 2017, 14(3): 685-702.
[3] Shu-Fen Tseng，Yen-Wei Tsao, Liang-ChihYu， Chien-lung Chan, K. & Robert Lai. Who will pass? Analyzing learners behaviors in MOOCs. [J]，Research and Practice in Technology Enhanced Learning, 2016, 11 (1)：1-11.
[4] Armando Fox. From MOOCs to SPOCs[J]. Communications of the ACM, 2013, 51(12): 38-40.
[5] Tim Goral. Make way for SPOCS：Small Private Online Courses May provide What MOOCs can’t [J]. University Business, 2013, 16(17): 45-46.
[6] Sun Yujie. Research of design and practice based on SPOC College Basic Computer Courses in the post MOOC [D], Hebei Normal University, 2016.
[7] Unal Cakiroglu. Analyzing the effect of learning styles and study habits of distance learners on learning performances：A case of an Introductory Programming Course [J]， International Review of Research in Open and Distance Learning, 2014, 15(4).
[8] Vasesen B E, Prins F J, Jeuring J. University students’s achievements goal and help seeing strategies in an intelligent tutoring system [J]. Computers & education, 2014 (72): 196-208.
[9] Peng Shaodong. A mining method model and its application of online learning behavior research in the era of big data [J]. E-education Research, 2017, 38(1): 72-81.
[10] ZHAO Huiqiong and so on. Empirical Research of Predictive Factors and Intervention Countermeasures of Online Learning Performance on Big Data-based Learning Analytics [J]. E-education Research, 2017, 38(1): 64-71.
[11] Li Kai, Gao Yan, Cao Zhe. Fuzzy clustering algorithm based on the automatic variable weights of samples and features[J]. Journal of Harbin Engineering University, 2018,39(09):1554-1560.
[12] Ye Qi-xiang, Han Zhen-jun, Jiao Jian-bin. Human detection in images via piecewise linear support vector machines [J]. IEEE Transactions on Image Processing, 2013, 22(2): 778-789.
[13] Zhou Su, Hu Zhe, Wen Zejun. A K Means/ Support Vector Machine based self-adaptive online fault diagnosis method for fuel cell system [J]. Journal of Tongji University,2019, 47(2): 255-260.
[14] Zhao Yang, Wang Sheng-wei, Xiao Fu. Pattern recognition-based chillers fault detection method using support vector data description (SVDD)[J]. Applied Energy, 2013, 112(1): 1041- 1048.
[15] Liang Jinjin, Wu De. Clustering piecewise double support vector domain classifier [J]. Control and Decision, 2015, 30(7): 1298-1302.
[16] Zou Bin，Peng Zhiming，Xu Zongben. The learning performance of support vector machine classification based on Markov sampling[J]. Science china information sciences, 2013， 56(3): 1-16.