XML Based Pre-processing and Analysis of Log Data in Adaptive E-Learning System: An Algorithmic Approach

  • Sucheta V. Kolekar
  • Radhika M. PaiEmail author
  • M. M. Manohara Pai
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 160)


E-learning has become the most popular way of delivering education and learning. Adaptive E-learning systems are the systems that adapt according to the requirements of the user. These systems should be capable of capturing the user preferences in terms of their learning styles and adapt the user interface accordingly. Web log analysis of the usage data can provide useful information regarding the learning styles. This analysis is extremely useful to develop an adaptive environment for the learner and at the same time for instructors to see how often their course contents are being used. In this paper a modified literature based approach is proposed where the learner’s behavior is tracked by capturing the interactions with e-learning portal. The captured behavior will be stored in the form of sessions which will be grouped together to generate the sequence files in the XML formats. The learning styles have been identified by an algorithmic approach based on the frequency and time that the learners spend on various learning components on the portal. The approach is useful to provide an adaptive user interface which includes adaptive contents and recommendations in learning environment to improve the efficiency of e-learning. The learning style model used is Felder-Silverman Learning Style Model (FSLSM) to fit the learning styles into an adaptive environment.


Adaptive E-learning Data pre-processing Usage patterns XML Felder-Silverman Learning Style Model 


  1. 1.
    Kolekar, S., Sanjeevi, S.S., Bormane, D.: Learning style recognition using artificial neural network for adaptive user interface in e-learning. In: Proceedings of IEEE Conference on Computational Intelligence and Computing Research (ICCIC), pp. 1–5. IEEE (2010)Google Scholar
  2. 2.
    Felder, R.M., Silverman, L.K.: Learning and teaching styles in engineering education. Engr. Edu. 78(7), 674–681 (2011)Google Scholar
  3. 3.
    Chiroma, H., Herawan, T., Deris, M.M., Abdullah, Z.: A sequential data preprocessing tool for data mining. In: Murgante, B., et al. (eds.) ICCSA 2014, Part III. LNCS, vol. 8581, pp. 734–746. Springer, Heidelberg (2014)Google Scholar
  4. 4.
    Romero, C., Romero, J.R., Ventura, S.: A survey on pre-processing educational data. In: Peña-Ayala, A. (ed.) Educational Data Mining. Studies in Computational Intelligence, vol. 524. Springer, cambridge (2013)Google Scholar
  5. 5.
    Tyagi, N.K., Solanki, A., Tyagi, S.: An algorithmic approach to data preprocessing in web usage mining. Int. J. Inf. Technol. Knowl. Manage. 2(2), 279–283 (2010)Google Scholar
  6. 6.
    Khosla, M.S., Bhojane, M.V.: Capturing web log and performing preprocessing of the users accessing distance education system. Int. J. Mod. Eng. Res. (IJMER) 2(5), 3128–3130 (2012)Google Scholar
  7. 7.
    Pamutha, T., Chimphlee, S., Kimpan, C., Sanguansat, P.: Data preprocessing on web server log files for mining users access patterns. Int. J. Res. Rev. Wirel. Commun. (IJRRWC) 2(2), 92–98 (2012)Google Scholar
  8. 8.
    Mödritscher, F., Andergassen, M., Neumann, G.: Dependencies between e-learning usage patterns and learning results. In: Proceedings of the 13th International Conference on Knowledge Management and Knowledge Technologies, pp. 24:1–24:8. ACM (2013)Google Scholar
  9. 9.
    Ortega, A.C., Blanco, R.R., Diaz, Y.Á.: Educational data mining: user categorization in virtual learning environments. In: Espin, R., Pérez, R.B., Cobo, A., Marx, J., Valdés, A.R. (eds.) Soft Computing for Business Intelligence. Studies in Computational Intelligence, vol. 537, pp. 225–237. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  10. 10.
    Munk, M., Drlík, M.: Impact of different pre-processing tasks on effective identification of users behavioral patterns in web-based educational system. Procedia Comput. Sci. 4, 1640–1649 (2011)CrossRefGoogle Scholar
  11. 11.
    Drlik, M., Munk, M.: Influence of different session timeouts thresholds on results of sequence rule analysis in educational data mining. In: Cherifi, H., Zain, J.M., El-Qawasmeh, E. (eds.) DICTAP 2011, Part I. CCIS, vol. 166, pp. 60–74. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  12. 12.
    Nukoolkit, C., Chansripiboon, P., Sopitsirikul, S.: Improving university e-learning with exploratory data analysis and web log mining. In: 2011 6th International Conference on Comput. Sci. Edu. (ICCSE), pp. 176–179. IEEE (2011)Google Scholar
  13. 13.
    Cápay, M., Balogh, Z., Boledovičová, M., Mesárošová, M.: Interpretation of questionnaire survey results in comparison with usage analysis in e-learning system for healthcare. In: Cherifi, H., Zain, J.M., El-Qawasmeh, E. (eds.) DICTAP 2011 Part II. CCIS, vol. 167, pp. 504–516. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  14. 14.
    Psaromiligkos, Y., Orfanidou, M., Kytagias, C., Zafiri, E.: Mining log data for the analysis of learners behaviour in web-based learning management systems. Oper. Res. 11(2), 187–200 (2011)Google Scholar
  15. 15.
    Langhnoja, S., Barot, M., Mehta, D.: Pre-processing: procedure on web log file for web usage mining. Int. J. Emerg. Technol. Adv. Eng. 2(12), 419–423 (2012)Google Scholar
  16. 16.
    Mahajan, R., Sodhi, J., Mahajan, V.: Usage patterns discovery from a web log in an indian e-learning site: a case study. J. Edu. Inf. Technol., 1–26 (2014). doi: 10.1007/s10639-014-9312-1 Google Scholar

Copyright information

© Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2016

Authors and Affiliations

  • Sucheta V. Kolekar
    • 1
  • Radhika M. Pai
    • 1
    Email author
  • M. M. Manohara Pai
    • 1
  1. 1.Department of Information and Communication Technology, Manipal Institute of TechnologyManipal UniversityManipalIndia

Personalised recommendations