Individualised training sheet composition of math word problems for learners with reading difficulties using genetic algorithm Online publication date: Mon, 28-Sep-2015
by K. Nandhini; S.R. Balasundaram
International Journal of Technology Enhanced Learning (IJTEL), Vol. 7, No. 2, 2015
Abstract: Performance in solving mathematical word problem (MWP) is closely related to readability skills. For a long time, it has been a challenge for trainers/instructors for providing exercises and examples related to meaningful mathematical word problems and demonstrating their applications in everyday life. This paper addresses a novel application of item selection to compose individualised training sheet for learners with reading difficulties using genetic algorithm. A modified crossover operator and mutation operator is used in finding optimal combination of questions. The integer based encoding helps in reducing the chromosome size. The efficiency and efficacy of the deployment of computer-based training rely mainly on the question selection based on the individual need. To provide a better training for learning difficulties in solving math word problems, individualised question selection using genetic algorithm (GA) is proposed in this work. In order to increase the interest of users during the training, individualised, non redundant, optimal difficulty level questions are composed. From the experimental results, it is evident that genetic algorithm approach works better in composing near optimal difficulty level training questions which are chosen from large a question bank than random approach (Baseline).
Online publication date: Mon, 28-Sep-2015
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Technology Enhanced Learning (IJTEL):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email firstname.lastname@example.org