Building a Personalized Multidimensional Intelligent Learning System

Currently, most of distance learning courses can only deliver standard material to students. Students receive course content passively which leads to the neglect of the goal of education – “to suit the teaching to the ability of students". Providing appropriate course content according to students- ability is the main goal of this paper. Except offering a series of conventional learning services, abundant information available, and instant message delivery, a complete online learning environment should be able to distinguish between students- ability and provide learning courses that best suit their ability. However, if a distance learning site contains well-designed course content and design but fails to provide adaptive courses, students will gradually loss their interests and confidence in learning and result in ineffective learning or discontinued learning. In this paper, an intelligent tutoring system is proposed and it consists of several modules working cooperatively in order to build an adaptive learning environment for distance education. The operation of the system is based on the result of Self-Organizing Map (SOM) to divide students into different groups according to their learning ability and learning interests and then provide them with suitable course content. Accordingly, the problem of information overload and internet traffic problem can be solved because the amount of traffic accessing the same content is reduced.

Authors:

• Lun-Ping Hung
• Nan-Chen Hsieh
• Chia-Ling Ho
• Chien-Liang Chen

Keywords:

• Distance Learning
• Intelligent Tutoring System(ITS)
• Self-Organizing Map (SOM)

References:

[1] P. De Bra, "Adaptive hypermedia," In H. H. Adelsberger, P. Kinshuk, J.
M. Pawlowski, and D. Sampson (Eds.), Handbook on information
technologies for education and training, pp. 29-46, Berlin:
Springer-Verlag, 2008.
[2] Naren Ramakrishnan and Saverio Perugini, "Personalizing Web sites with
mixed-initiative interaction," IT Professional, vol. 5(2), pp. 9 - 15, 2003.
[3] Rahul Agarwal, Stephen H. Edwards, and Manuel A, "Pérez-Qui├▒ones,
Designing an adaptive learning module to teach software testing," ACM
SIGCSE Bulletin, vol. 38(1), pp. 259-263, 2006.
[4] Patricia L. Carrell, "Content and Formal Schemata in ESL Reading,"
TESOL Quarterly, vol. 21, no.3, pp. 461-481, September, 1987.
[5] E. F. Patten, "The influence of distribution of repetitions on certain rote
learning phenomena," Journal of Psychology: Interdisciplinary and
Applied, vol. 5, pp. 359-374, 1938.
[6] P.A. Cohen, J.A. Kulik, and C.C. Kulik, "Educational outcomes of
tutoring: A meta analysis of findings," American Educational Research
Journal, vol. 19, pp. 237-248,1982.
[7] Qingzhao Tan, Prasenjit Mitra, and C. Lee Giles, "Designing
clustering-based web crawling policies for search engine crawlers," in
Proc. 16th ACM conference on Conference on information and
knowledge management, Lisbon, Portugal, 2007, pp. 535-544.
[8] Mehdi Hosseini and Hassan Abolhassani, "Mining Search Engine Query
Log for Evaluating Content and Structure of a Web Site," in Proc. The
IEEE/WIC/ACM International Conference on Web Intelligence, Silicon
Valley, USA, 2007, pp. 235-241.
[9] Horng-Jinh Chang, Lun-Ping Hung, and Chia-Ling Ho, "An anticipation
model of potential customers- purchasing behavior based on clustering
analysis and association rules analysis", Expert Systems with
Applications, vol. 32, pp. 753-764, August, 2007.
[10] S. Asharaf, M. Narasimha Murty, and S.K. Shevade, "Rough set based
incremental clustering of interval data," Pattern Recognition Letters, vol.
27, pp. 515-519, 2006.