International Journal of Electrical and Computer Engineering (IJECE) Vol. 10, No. 4, August 2020, pp. 4372~4380 ISSN: 2088-8708, DOI: 10.11591/ijece.v10i4.pp4372-4380  4372 Journal homepage: http://ijece.iaescore.com/index.php/IJECE Random forest application on cognitive level classification of E-learning content Benny Thomas, Chandra J. Department of Computer Science, CHRIST (Deemed to be University), India Article Info ABSTRACT Article history: Received Dec 19, 2019 Revised Mar 3, 2020 Accepted Mar 14, 2020 The e-learning is the primary method of learning for most learners after the regular academics studies. The knowledge delivery through E-learning technologies increased exponentially over the years because of the advancement in internet and e-learning technologies. Knowledge delivery to some people would never have been possible without the e-learning technologies. Most of the working professional do focused studies for carrier advancement, promotion or to improve the domain knowledge. These learner can find many free e-learning web sites from the internet easily in the domain of interest. However it is quite difficult to find the best e-learning content suitable for their learning based on their domain knowledge level. User spent most of the time figuring out the right content from a plethora of available content and end up learning nothing. An intelligent framework using machine learning algorithms with random forest Classifier is proposed to address this issue, which classifies the e-learning content based on its difficulty levels and provide the learner the best content suitable based on the knowledge level .The frame work is trained with the data set collected from multiple popular e-learning web sites. The model is tested with real time e-learning web sites links and found that the e-contents in the web sites are recommended to the user based on its difficulty levels as beginner level, intermediate level and advanced level. Keywords: Blooms taxonomy Difficulty level E-learning Machine learning Random forest classifier Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Benny Thomas, Department of Computer Science, CHRIST (Deemed to be University), India. Email: benny.thomas@res.christuniversity.in 1. INTRODUCTION E-learning is a popular learning method with the help of internet and other e-learning technologies. It bridges the geographical gap between the learner and teacher. E-learning become popular with the advancement in e-learning technologies and the availability of world class e-learning web sites. Currently it is the primary method of learning for most of the working professional and entrepreneurs. E-learning gives us the choice and flexibility to learn from anywhere and at any time. Because of its wider usage and potentiality, the e-learning web sites increased exponentially over the years. It is easy for any learners to find multiple e-learning web sites needed for their domain. However because of the availability of many web sites, the user most of the time get overwhelmed with the magnitude of content availability and find it difficult to understand and choose the right learning content. User spent most of the time trying to figure out the content to be chosen and end up learning nothing significant to improve the knowledge. This situation can be managed by providing intelligent content recommendations based on the domain knowledge level of the user which helps to find the right learning content. Different approaches were used to address this issue. Some of the methods used are recommended systems, good learners rating, association rule mining, learner grouping, item set mining etc.