Gramoli, V and Charleston, M and Jeffries, B and Koprinska, I and McGrane, M and Radu, A and Viglas, A and Yacef, K, Mining autograding data in computer science education, Proceedings of the Australasian Computer Science Week Multiconference, 02-05 February 2016, Canberra, Australia, pp. 1-10. ISBN 978-1-4503-4042-7 (2016) [Refereed Conference Paper]
Copyright 2016 ACM
In this paper we present an analysis of the impact of instant feedback and autograding in computer science education, beyond the classic Introduction to Programming subject.
We analysed the behaviour of 1st year to 4th year students when submitting programming assignments at the University of Sydney over a period of 3 years. These assignments were written in different programming languages, such as C, C++, Java and Python, for diverse computer science courses, from fundamental ones - algorithms, complexity, formal languages, data structures and artificial intelligence to more "practical" ones - programming, distributed systems, databases and networks.
We observed that instant feedback and autograding can help students and instructors in subjects not necessarily focused on programming. We also discuss the relationship between the student performance in these subjects and the choice of programming languages or the times at which a student starts and stops working on an assignment.
|Item Type:||Refereed Conference Paper|
|Keywords:||educational data mining, isntant feedback, learning analytics|
|Research Group:||Education Systems|
|Research Field:||Higher Education|
|Objective Division:||Education and Training|
|Objective Group:||Teaching and Instruction|
|Objective Field:||Teaching and Instruction Technologies|
|Author:||Charleston, M (Associate Professor Michael Charleston)|
|Deposited By:||Mathematics and Physics|
Repository Staff Only: item control page