A framework for personalized competitive programming training

Programming Contests are a special branch in the general area of training and education programming support and cover an important role in the area of computer science. Rather than the direct provision of concepts and exercises related to programming, the main concern is on the algorithms and data structures managed while composing the solution to a problem, and the quality of the solution program itself. Training via web for programming contests is mainly comprised of the activity of producing solutions to problems offered by the online system (online training platforms), whereas a solution is a program, submitted by the student, and it has to be evaluated, in order to assess the programming performance, and give suggestions about the quality of the solution, so to make the experience an informative (learning) one. To the best of our knowledge, supporting a personalized approach and possibly recommendations given by the system, is a challenge. In this paper we tackle the problem of supporting students in their online training toward the participation in a programming contest, aiming at defining a framework that can allow recommendations, under the form of suggestions, to the learner, about the next programming problem to undertake, and that can foster motivation in students by means of a lightweight, badge-based, gamified approach.