A Recommender System for Supporting Students in Programming Online Judges
Programming Online Judges (POJs) are tools that contain a large collection of programming problems to be solved by students as a component of their training and programming practices. This contribution presents a recommendation approach to suggest to students the more suitable problems to solve for increasing their performance and motivation in POJs. Some key features of the approach are the use of an enriched user-problem matrix that incorporates specific information related to the user performance in the POJ, and the development of a strategy for natural noise management in such a matrix. The experimental evaluation shows the improvements of the proposal as compared to previous works.
KeywordsProgramming online judges Problems recommendation Natural noise management
This research work was partially supported by the Spanish National research project TIN2015-66524-P, the Spanish Ministry of Economy and Finance Postdoctoral Fellow (IJCI-2015-23715), the Spanish FPU fellowship (FPU13/01151) and ERDF.
- 2.Amatriain, X., Pujol, J.M.: Data mining methods for recommender systems. In: Recommender Systems Handbook, pp. 227–262. Springer (2015)Google Scholar
- 3.Caiza, J., Del Amo, J.: Programming assignments automatic grading: review of tools and implementations. In: Proceedings of INTED 2013, pp. 5691–5700 (2013)Google Scholar
- 16.Vesin, B., Klašnja-Milićević, A., Ivanović, M., Budimac, Z.: Applying recommender systems and adaptive hypermedia for e-learning personalization. Comput. Inform. 32(3), 629–659 (2013)Google Scholar