Publications
Permanent URI for this collectionhttps://repositorio.grial.eu/handle/123456789/34
Browse
2 results
Search Results
Item Teaching and learning strategies of programming for university courses(ACM, 2019-10-16) Figueiredo, J.; García-Peñalvo, F. J.It is consensual to consider teaching and learning programming difficult. A lot of work, dedication, and motivation are required for teachers and students. Since the first programming languages have emerged, the problem of teaching and learning programming is studied and investigated. The theme is very serious, not only for the important concepts underlying the course but also for the lack of motivation, failure, and abandonment that such frustration may imply in the student. Immediate response and constant monitoring of students' activities and problems are important. With this work, it is our goal to improve student achievement in courses where programming is essential. We want each student to be able to improve and deepen their programming skills, performing a set of exercises appropriate and worked for each student and situation. We intend to build a dynamic learning model of constant evaluation, build the profile of the student. The student profile will be analyzed by our predictive model, which in case of prediction of failure, the student will have more careful attention. Predict the student's failure with anticipation and act with specific activities, giving the student the possibility of training and practicing the activities with difficulties. With this model, we try to improve the skills of each student in programming.Item Predicting Student Failure in an Introductory Programming Course with Multiple Back-Propagation(ACM, 2019-10-16) Figueiredo, J.; Lopes, N.; García-Peñalvo, F. J.One of the most challenging tasks in computer science and similar courses consists of both teaching and learning computer programming. Usually this requires a great deal of work, dedication, and motivation from both teachers and students. Accordingly, ever since the first programming languages emerged, the problems inherent to programming teaching and learning have been studied and investigated. The theme is very serious, not only for the important concepts underlying computer science courses but also for reducing the lack of motivation, failure, and abandonment that result from students frustration. Therefore, early identification of potential problems and immediate response is a fundamental aspect to avoid student’s failure and reduce dropout rates. In this paper, we propose a machine-learning (neural network) predictive model of student failure based on the student profile, which is built throughout programming classes by continuously monitoring and evaluating student activities. The resulting model allows teachers to early identify students that are more likely to fail, allowing them to devote more time to those students and try novel strategies to improve their programming skills.