Abstract
In the current era, multiple disciplines struggle with the scarcity of data, particu-larly in the area of e-learning and social learning. In order to test their ap-proaches and their recommendation systems, researchers need to ensure the availability of large databases. Nevertheless, it is sometimes challenging to find-out large scale databases, particularly in terms of education and e-learning. In this article, we outline a potential solution to this challenge intended to improve the quantity of an existing database. In this respect, we suggest genetic algo-rithms with some adjustments to enhance the size of an initial database as long as the generated data owns the same features and properties of the initial data-base. In this case, testing machine learning and recommendation system ap-proaches will be more practical and relevant. The test is carried out on two da-tabases to prove the efficiency of genetic algorithms and to compare the struc-ture of the initial databases with the generated databases. The result reveals that genetic algorithms can achieve a high performance to improve the quantity of existing data and to solve the problem of data scarcity.
Highlights
E-learning is proving to occupy a major position in providing online courses and education [1]
Obolo (2018) allow the usage of genetic algorithms to generate an optimal path through the identification of the level of difficulty of online courses and the courses that correspond to the learners' needs [11]
In order to analyze the results obtained in both cases on the basis of genetic algorithms, it is initially required to define the different parameters under consideration
Summary
E-learning is proving to occupy a major position in providing online courses and education [1]. The concept of social learning is generally associated with social networks, which are experiencing a high level of activity as a result of high user demand [2, 3, 4]. The performance of Machine Learning algorithms decreases when the database is not of considerable volume. In this regard, we propose genetic algorithms with some adjustments as a solution to increase our data and to test our recommendation approach in a more trustworthy way. We perform the test on two databases of different sizes, and afterwards we apply genetic algorithms to generate additional data. A conclusion summarizes all the work performed and the directions to be pursued
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Emerging Technologies in Learning (iJET)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
