Genetic Algorithms in Education

In online education, there a variety of interactive group activities categorized as collaborative learning. Discussion forums is one such example of a collaborative learning strategy, group/partner project work is another. Where group dynamics play a more significant role in the learning process than other types of teaching methods, getting the right mixture of students together can have a significant effect on learning outcomes [1].

In their paper, Liu and Chuchu Li [1] describe a grouping strategy for a personalized collaborative learning system that uses a ‘combination of genetic algorithm and K-means algorithm’. This two step process involves first clustering students into categories according to their interest in the course, their learning ability and personality. After selecting one individual from each of those categories, the genetic algorithm is used to optimize the arrangement of individuals in groups of 3-5.

Chen and Yang [2] employ an evolutionary algorithm to search for the best grouping scheme within a population of students as well. As in the previously mentioned paper, knowing something about the students, such as level of interest and level of knowledge is important, as is having a good model for what makes an effective group. The evolutionary algorithm searches for similar levels of knowledge within the group and different levels of knowledge between the groups in order to come up with an optimized grouping strategy.

While personalized learning is not a new idea, implementing it in a networked environment will continue to be a future research direction for genetic algorithms in education. Specific applications where the optimization benefit of genetic algorithms can be useful are in personalized curriculum generation [3], personalized content organization/optimization [4] and scheduling or timetabling optimizations [5].

References:

[1] Liu, Lizhen; Chuchu Li; Chao Du, “The design of personalized Collaborative Learning System,” in IT in Medicine and Education (ITME), 2011 International Symposium on , vol.1, no., pp.49-53, 9-11 Dec. 2011
doi: 10.1109/ITiME.2011.6130781

[2] Chen Long; Yang Qing-hong, “A group division method based on collaborative learning elements,” in Control and Decision Conference (2014 CCDC), The 26th Chinese , vol., no., pp.1701-1705, May 31 2014-June 2 2014
doi: 10.1109/CCDC.2014.6852443

[3] Jebari, K.; El moujahid, A.; Bouroumi, A.; Ettouhami, A., “Genetic algorithms for online remedial education based on competency approach,” in Multimedia Computing and Systems (ICMCS), 2011 International Conference on , vol., no., pp.1-6, 7-9 April 2011
doi: 10.1109/ICMCS.2011.5945603

[4] Chiou, C.-K., Tseng, J.C.R., Hwang, G.-J., and Heller, S. 2010. An adaptive navigation support system for conducting context-aware ubiquitous learning in museums. Comput. Educ. 55, 2 (Sep. 2010), 834–845. DOI= 10.1016/j.compedu.2010.03.015

[5] Shengxiang Yang; Jat, S.N., “Genetic Algorithms With Guided and Local Search Strategies for University Course Timetabling,” in Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on , vol.41, no.1, pp.93-106, Jan. 2011
doi: 10.1109/TSMCC.2010.2049200

Creative Commons License
Genetic Algorithms in Education by Brad is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Brad

Brad Payne is currently the lead developer for the Open Textbook Project whose work focuses on open source software using PHP (LAMP).

When not contributing to other developers’ projects on github, he builds his own. Through exploiting API’s and with a penchant for design patterns, he helps BCcampus implement new technologies for post-secondary institutions. Prior to his current position at BCcampus, Brad worked in IT at Camosun College and the BC Ministry of Education.

You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *

*