A Recommended Feedback Model of a Programming Exercise Using Clustering-Based Group Assistance
S. Suhailan1, M.S. Mat Deris2, S. Abdul Samad3, M.A. Burhanuddin4
1S. Suhailan, Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
2M.S. Mat Deris., Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia.
3S. Abdul Samad, Universiti School of Information Technology, Faculty of Business & Information Science (FoBIS), UCSI University, Kuala Lumpur, Malaysia.
4M.A. Burhanuddin, Faculty of Information Communication Technology, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia.
Manuscript received on 16 February 2019 | Revised Manuscript received on 07 March 2019 | Manuscript Published on 08 June 2019 | PP: 638-646 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E11330275S419/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Many studies on automated programming assessment tools with automated feedbacks have been addressed to assist students rectifying their solution’s difficulty. While several studies have produced specific computational programming exercise’s feedback using a static template analysis, there is still a lack of an automated programming feedback model that is dynamically enriched through a live assisted feedback from an expert. Thus, this research proposed a recommended feedback model on specific computational programming question using clustering-based live group assistance. The assisted feedback was done by an expert through a similar difficulty analysis of computer programs that were grouped together based on ordinal features using a K-Means clustering algorithm. An experiment was executed by responding to 7 program difficulty clusters that consists of 33 programs. Based on these inputs, the efficiency ratio result shows that the model can minimize expert’s workload and can be effectively used as a recommender system. Furthermore, the efficiency of this model can be gradually intensified with more assisted feedbacks being provided by the expert user within other lab sessions.
Keywords: K-Means, Programming Feedback, Recommender System.
Scope of the Article: Clustering