Prior programming knowledge of students has a major impact on introductory programming courses. Those with prior experience often seem to breeze through the course. Those without prior experience see others breeze through the course and disengage from the material or drop out. The purpose of this study is to demonstrate that novice student programming behavior can be modeled as a Markov process. The resulting transition matrix can then be used in machine learning algorithms to create clusters of similarly behaving students. We describe in detail the state machine used in the Markov process and how to compute the transition matrix. We compute the transition matrix for 665 students and cluster them using the k-means clustering algorithm. We choose the number of cluster to be three based on analysis of the dataset. We show that the created clusters have statistically different means for student prior knowledge in programming, when measured on a Likert scale of 1-5.
In a previous publication we examined the connections between high-school computer science (CS) and computing higher education. The results were promising—students who were exposed to computing in high school were more likely to take one of the computing disciplines. However, these correlations were not necessarily causal. Possibly those students who took CS courses, and especially high-level CS courses in high school, were already a priori inclined to pursue computing education. This uncertainty led us to pursue the current research. We aimed at finding those factors that induced students to choose CS at high school and later at higher-education institutes. We present quantitative findings obtained from analyzing freshmen computing students' responses to a designated questionnaire. The findings show that not only did high-school CS studies have a major impact on students’ choice whether to study computing in higher education—it may have also improved their view of the discipline.
Distance Learning has enabled educational practices based on digital platforms, generating massive amounts of data. Several initiatives use this data to identify dropout contexts, mainly providing teacher support about student behavior. Approaches such as Active Methodologies are known as having good potential to involve and motivate students. This article presents a systematic mapping aiming to identify current Educational Data Mining and Learning Analytics methods. Besides, we identify Active Methodologies’ application to mitigate dropout in Distance Learning. We evaluated 668 papers published from January 2015 to March 2020. The results indicate a growing application of Educational Data Mining and Learning Analytics to identify and mitigate students’ abandonment in Distance Learning. However, studies with Active Methodologies to minimize dropout and enhance student permanence are scarce. Some works suggest Active Methods as a possible complement of Learning Analytics in dropout.
Although Machine Learning (ML) is integrated today into various aspects of our lives, few understand the technology behind it. This presents new challenges to extend computing education early to ML concepts helping students to understand its potential and limits. Thus, in order to obtain an overview of the state of the art on teaching Machine Learning concepts in elementary to high school, we carried out a systematic mapping study. We identified 30 instructional units mostly focusing on ML basics and neural networks. Considering the complexity of ML concepts, several instructional units cover only the most accessible processes, such as data management or present model learning and testing on an abstract level black-boxing some of the underlying ML processes. Results demonstrate that teaching ML in school can increase understanding and interest in this knowledge area as well as contextualize ML concepts through their societal impact.
The International Olympiad in Informatics (IOI) aspires to be a science olympiad alongside such international olympiads in mathematics, physics, chemistry, and biology. Informatics as a discipline is well suited to a scientific approach and it offers numerous possibilities for competitions with a high scientific standing. We argue that, in its current form, the IOI fails to be scientific in the way it evaluates the work of the contestants.
In this paper, we describe the major ingredients of the IOI to guide further discussions. By presenting the results of an extensive analysis of two IOI competition tasks, we hope to create an awareness of the urgency to address the shortcomings. We offer some suggestions to raise the scientific quality of the IOI.