Comparison of Different Feature Selection Techniques in Attribute Selection of Learning Style Prediction

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Learning style of specific users on an online learning system is determined based on their interaction and behavior towards the system. The most common online learning theory used in determining the learning style is the Felder-Silverman’s Theory. Many researchers have proposed machine learning algorithms to establish learning style by using the log file attributes. Due to many attributes in predicting the learning style, the performance and efficiency of the classification and prediction are still poor; so far it is only between 58%-85%. This research is conducted to determine the most relevant attributes in predicting the learning style. First, three different feature selection methods are used to select the most relevant number of attributes, which are Rank by Importance (RbI), Recursive Feature Elimination (RFE) and Correlation. Next, five different classifiers are used to evaluate those selected feature selection methods. The classifiers are Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbour (KNN), Linear Discriminant Analysis (LDA) and Classification and Regression Tree (CART). From the experiments, RbI has proven to be the most effective feature selection method, with the accuracy improvement from 87% to 91%.

     

     


  • Keywords


    Classification Algorithm; Feature Selection; Learning Style; Online Learning.

  • References


      [1] R. M. Felder and L. K. Silverman, “Learning and teaching styles in engineering education”, Engineering education, Vol. 78, no. 7, (1988) pp. 674–681.

      [2] H. M. Truong, “Integrating learning styles and adaptive e-learning system: Current developments, problems and opportunities”, Com- puters in Human Behavior, vol. 55, (2016), pp. 1185–1193.

      [3] R. Mokhtar, N. A. M. Zin, and S. N. H. S. Abdullah, “Rule-based knowledge representation for modality learning style in aiwbes”, Knowledge Management International Conference, 2010.

      [4] J. Bernard, T.-W. Chang, E. Popescu, and S. Graf, “Learning style identifier: Improving the precision of learning style identification through computational intelligence algorithms”, Expert Systems with Applications, vol. 75, (2017), pp. 94–108.

      [5] R. R. Maaliw III, “Classification of learning styles in virtual learn- ing environment using data mining: A basis for adaptive course design,” 2016.

      [6] Y. Kim, W. N. Street, and F. Menczer, “Feature selection in data mining”, Data mining: opportunities and challenges, vol. 3, no. 9, (2003),pp. 80–105.

      [7] J. Miao and L. Niu, “A survey on feature selection”, Procedia Computer Science, vol. 91, (2016), pp. 919–926.

      [8] G. T. Hilda and R. Rajalaxmi, “Effective feature selection for supervised learning using genetic algorithm”, in Electronics and Communication Systems (ICECS), (2015), pp. 909–914.

      [9] T. A. Litzinger, S. H. Lee, and J. C. Wise, “A study of the reliability and validity of the felder-soloman index of learning styles,” 2005.

      1. D. Benson, “Using online learning to meet workforce demand:A case study of stakeholder influence”, Quarterly review of distance education, vol. 3, no. 4, (2002), pp. 443–452.

      [10] J. L. Moore, C. Dickson-Deane, and K. Galyen, “e-learning, online learning, and distance learning environments: Are they the same?”, The Internet and Higher Education, vol. 14, no. 2, (2011), pp. 129–135.

      [11] D.Conrad, “Deep in the hearts of learners: Insights into the nature of online community,” International Journal of E-Learning & Distance Education, vol. 17, no. 1, (2002), pp. 1–19.

      [12] S. Gao, G. Ver Steeg, and A. Galstyan, “Variational information maximization for feature selection”, Advances in Neural Informa- tion Processing Systems, (2016), pp. 487–495.

      [13] N. S´anchez-Maro˜no, A. Alonso-Betanzos, and M. Tombilla- Sanrom´an, “Filter methods for feature selection–a comparative study,” in International Conference on Intelligent Data Engineering and Automated Learning. Springer, 2007, pp. 178–187.

      [14] D. J. K. L. Selvapriya M, “Data mining in education”, Interna- tional Journal of Multidisciplinary Research and Development, vol. 3, no. 3, (2016), pp. 43–48.

      [15] B. Pradhan, “A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy mod- els in landslide susceptibility mapping using gis”, Computers & Geosciences, vol. 51, (2013), pp. 350–365.

      [16] H. Parvin, H. Alizadeh, and B. Minaei-Bidgoli, “Mknn: Modi- fied knearest neighbor”, Proceedings of the World Congress on Engineering and Computer Science, vol. 1. Citeseer, 2008.

      [17] L.Breiman, “Random forests,”Machine lerning, vol. 45, no. 1, (2001), pp. 5-32.

      [18] J. –J. Lo, Y.-C. Chan, and S.-W. Yeh, “Designing an adaptive web-based learning system based on students coginitive styles identified online”, Computers & Education, vol. 58, no.1, (2012),pp.209-222.

      [19] L. T.-C. Graf, Sabine et al., “Supporting teachers in identifying students’ learning styles in learning management systems: An automatic student modelling approach”, Journal of Educational Technology Society, vol.12, no. 4, (2009), p.3.


 

View

Download

Article ID: 23336
 
DOI: 10.14419/ijet.v7i4.31.23336




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.