Early and precisely predicting the students’ dropout based on available educational data belongs to the widespread research topic of the learning analytics research field. Despite the amount of already realized research, the progress is not significant and persists on all educational data levels. Even though various features have already been researched, there is still an open question, which features can be considered appropriate for different machine learning classifiers applied to the typical scarce set of educational data at the e-learning course level. Therefore, the main goal of the research is to emphasize the importance of the data understanding, data gathering phase, stress the limitations of the available datasets of educational data, compare the performance of several machine learning classifiers, and show that also a limited set of features, which are available for teachers in the e-learning course, can predict student’s dropout with sufficient accuracy if the performance metrics are thoroughly considered. The data collected from four academic years were analyzed. The features selected in this study proved to be applicable in predicting course completers and non-completers. The prediction accuracy varied between 77 and 93% on unseen data from the next academic year. In addition to the frequently used performance metrics, the comparison of machine learning classifiers homogeneity was analyzed to overcome the impact of the limited size of the dataset on obtained high values of performance metrics. The results showed that several machine learning algorithms could be successfully applied to a scarce dataset of educational data. Simultaneously, classification performance metrics should be thoroughly considered before deciding to deploy the best performance classification model to predict potential dropout cases and design beneficial intervention mechanisms.

Understanding how software works and writing a program are currently frequent requirements when hiring employees. The complexity of learning programming often results in educational failures, student frustration and lack of motivation, because different students prefer different learning paths. Although e-learning courses have led to many improvements in the methodology and the supporting technology for more effective programming learning, misunderstanding of programming principles is one of the main reasons for students leaving school early. Universities face a challenging task: how to harmonise students’ education, focusing on advanced knowledge in the development of software applications, with students’ education in cases where writing code is a new skill. The article proposes a conceptual framework focused on the comprehensive training of future programmers using microlearning and automatic evaluation of source codes to achieve immediate feedback for students. This framework is designed to involve students in the software development of virtual learning environment software that will provide their education, thus ensuring the sustainability of the environment in line with modern development trends. The paper’s final part is devoted to verifying the contribution of the presented elements through quantitative research on the introductory parts of the framework. It turned out that although the application of interactive features did not lead to significant measurable progress during the first semester of study, it significantly improved the results of students in subsequent courses focused on advanced programming.

Educational Data Mining and learning analytics have gained significant prominence in recent years, garnering attention from researchers worldwide. This is primarily due to their potential to improve decision-making processes within higher education. This study utilizes Educational Data Mining to suggest a clustering-based approach for classifying students based on their academic performance, specifically focusing on their interactions within Learning Management Systems in blended learning settings. Log data from the Learning Management System Moodle platform was analyzed to determine if valuable insights could be derived from student activities without the need for personal or invasive data. Given the large dataset, Principal Component Analysis and Uniform Manifold Approximation and Projection were employed for dimensionality reduction. Three unsupervised learning models—BIRCH, DBSCAN, and GMM—were then applied to identify distinct student clusters. The results from the comparison revealed that the BIRCH algorithm was the most effective in accurately categorizing students based on their activities. Further analysis of these clusters showed a significant correlation between student engagement and academic outcomes, with two high-risk clusters identified as having the highest dropout rates. To better understand the reasons behind the found clusters, the course duration was subsequently divided into intervals, and standard machine learning methods were applied to predict at-risk students over time, confirming that early identification of at-risk students using clustering is feasible. This study demonstrates the efficacy of non-invasive data collection and unsupervised learning models in predicting student success, emphasizing the importance of temporal and content-specific analysis. The proposed approach enhances understanding of student behavior and supports the development of targeted interventions to improve student retention and achievement.

The number of students who decided to study information technology related study programs is continually increasing. Introductory programming courses represent the most crucial milestone in information technology education and often reflect students’ ability to think abstractly and systematically, solve problems, and design their solutions. Even though many students who attend universities have already completed some introductory courses of programming, there is still a large group of students with limited programming skills. This drawback often increases during the first term, and it is often the main reason why students leave study too early. There is a myriad of technologies and tools which can be involved in the programming course to increase students’ chances of mastering programming. The introductory programming courses used in this study has been gradually extended over the four academic years with the automated source code assessment of students’ programming assignments followed by the implementation of a set of suitably designed microlearning units. The final four datasets were analysed to confirm the suitability of automated assessment and microlearning units as predictors of at-risk students and students’ outcomes in the introductory programming courses. The research results proved the significant contribution of automated code assessment in students’ learning outcomes in the elementary topics of learning programming. Simultaneously, it proved a moderate to strong dependence between the students’ activity and achievement in the activities and final students’ outcomes.

Analyzing the unique types of data that come from educational systems can help find the most effective structure of the elearning courses, optimize the learning content, recommend the most suitable learning path based on student's behavior, or provide more personalized environment. We focus only on the processes involved in the data preparation stage of web usage mining. Our objective is to specify the inevitable steps that are required for obtaining valid data from the stored logs of the webbased educational system. We compare three datasets of different quality obtained from logs of the web-based educational system and pre-processed in different ways: data with identified users’ sessions and data with the reconstructed path among course activities. We try to assess the impact of these advanced techniques of data pre-processing on the quantity and quality of the extracted rules that represent the learners’ behavioral patterns in a web-based educational system. The results confirm some initial assumptions, but they also show that the path reconstruction among visited activities in e-leaning course has not statistically significant effect on quality and quantity of the extracted rules.