Abstract. This paper presents a systematic literature review (SLR) about algorithms and programming teaching for beginner students in Brazilian higher education. Those courses are called CS1 (Computer Science 1) for short. The review was conducted on papers published in the following Brazilian conferences: SBIE, WIE, WEI and WAAAP between the years 2001 and 2014. This work searches for empirical evidences about the artefacts that influence success/failure rates in CS1 courses. Furthermore, the results of this review are compared to international results. From 394 papers selected 49 where analysed, but only 7 presented failure rates before and after experimentation. The failure rate on those papers was observed to be reduced from 45.6 to 32.6% after experimentation.Resumo. Este artigo apresenta uma revisão sistemática da literatura (RSL) sobre o ensino de programação e algoritmos para alunos iniciantes do ensino superior brasileiro, chamados CS1 (Computer Science 1). A RSL foi realizadà a partir da revisão dos artigos publicados nos eventos SBIE, WIE, WEI e WA-AAP entre os anos de 2001 a 2014. Este trabalho busca evidências empíricas dos artefatos que influenciam as taxas de sucesso/reprovação nos cursos CS1. Além disso, procurou-se comparar resultados desta revisão com os resultados apresentados internacionalmente. Do total de 394 artigos pré-selecionados, restaram 49, dos quais apenas 7 artigos apresentam taxas de reprovação de alunos antes e depois da realização do(s) experimento(s), reduzindo essa taxa, em média, de 45,6% para 32,6%.

This paper describes the application of Data Science and Educational Data Mining techniques to data from 4529 students, seeking to identify behavior patterns and generate early predictive models at the Universidad de la República del Uruguay. The paper describes the use of data from different sources (a Virtual Learning Environment, survey, and academic system) to generate predictive models and discover the most impactful variables linked to student success. The combination of different data sources demonstrated a high predictive power, achieving prediction rates with outstanding discrimination at the fourth week of a course. The analysis showed that students with more interactions inside the Virtual Learning Environment tended to have more success in their disciplines. The results also revealed some relevant attributes that influenced the students’ success, such as the number of subjects the student was enrolled in, the students’ mother’s education, and the students’ neighborhood. From the results emerged some institutional policies, such as the allocation of computational resources for the Virtual Learning Environment infrastructure and its widespread use, the development of tools for following the trajectory of students, and the detection of students at-risk of failure. The construction of an interdisciplinary exchange bridge between sociology, education, and data science is also a significant contribution to the academic community that may help in constructing university educational policies.

Algorithms and programming are some of the most challenging topics faced by students during undergraduate programs. Dropout and failure rates in courses involving such topics are usually high, which has raised attention towards the development of strategies to attenuate this situation. Machine learning techniques can help in this direction by providing models able to detect at-risk students earlier. Therefore, lecturers, tutors or staff can pedagogically try to mitigate this problem. To early predict at-risk students in introductory programming courses, we present a comparative study aiming to find the best combination of datasets (set of variables) and classification algorithms. The data collected from Moodle was used to generate 13 distinct datasets based on different aspects of student interactions (cognitive presence, social presence and teaching presence) inside the virtual environment. Results show there are no statistically significant difference among models generated from the different datasets and that the counts of interactions together with derived attributes are sufficient for the task. The performances of the models varied for each semester, with the best of them able to detect students at-risk in the first week of the course with AUC ROC from 0.7 to 0.9. Moreover, the use of SMOTE to balance the datasets did not improve the performance of the models.

No abstract

In adaptive hypertexts the user is guided in two ways: through the existence of links and through link annotation or hiding. Link structures have been investigated, starting with Botafogo et al, and the effect of link annotation has been studied, for instance by Brusilovsky et al. This paper studies the combined effect of link structure and annotation/hiding on the navigation patterns of users. It defines empirical hubs and studies their correlation with hubs as defined by Kleinberg without considering adaptation. The data for the analysis have been extracted from the logs of the course "Hypermedia Structures and Systems," an online adaptive course offered at the Eindhoven University of Technology.