Big data analytics framework to analyse student's performance. (21st November 2019)

• Record Type: Journal Article
• Authors: Lakshmi, Vempati Amrutha; Meena, M. Janaki; Ibrahim, S.P. Syed
• Is Part Of: International journal of computational complexity and intelligent algorithms. Volume 1:Number 2(2019)
• Page Start: 154
• Page End: 164
• Publication Date: 2019-11-21
• Subjects: big data analytics -- reflective learning -- teaching; Computational complexity -- Periodicals; Heuristic algorithms -- Periodicals; Neural networks (Computer science) -- Periodicals; 006.3
• Languages: English
• ISSNs: 2048-4720

Abstract

Performance of the students is the most important element for any educational institution. Knowing the areas where student lags proficiency helps the student as well as the teacher to improve and make the education system to be in par with this competitive world. Aim of this paper is to provide a framework that can analyse the performance of the students. This framework was experimented with a first semester course which has 5, 962 students registered. Students were given a problem, taught programming concepts relevant to solving it and they are made to experiment them immediately on a machine. Three categories of exercises practice problems; assessment problems and challenging task were given to the students through an online portal. Rubrics were designed to evaluate the performance of students. A scalable MapReduce-based analytics model using Spark framework was developed and results were visualised. Then K-means clustering algorithm was also applied to group the students based on their performance.