This research WIP paper describes the case of a first-year engineering course which, contrary to modern trends in education, reduced the presence of blended learning in its methodology, transitioning from the flipped classroom and intensive continuous assessment models back to traditional instruction. Typically, blended learning methodologies like the flipped classroom are regarded to have the positive effects of improving engagement and fostering a student-centered learning approach. However, there are also concerns regarding the potentially increased workload that this system imposes on students. This study analyzes course resource usage trends by students, comparing the final year under the blended learning method with the first year after the switch to traditional instruction. More specifically, the volume of student activity, its timing throughout the semester, and the preferred types of resources are compared between both methodologies. The study found that, in terms of time spent interacting with resources, there was not a significant decrease between both iterations of the course, although the types of resources favored by students do vary between methodologies. Additionally, the activity distribution throughout the semester is observed to be heavily influenced by the timing of exams in both scenarios.

This research WIP paper describes the DACEM project, aimed at enhancing course catalogues to support the objectives of the Erasmus+ program. Within Erasmus+, course catalogues serve as essential tools for students in their quest for suitable academic opportunities and for institutions in negotiating bilateral agreements on shared programs. Despite numerous initiatives and years of experience, European higher education institutions still face significant challenges in providing appropriate course catalogues, which directly impacts student mobility. This paper conducts an analysis of the current course catalogues situation in 7 European countries (Estonia, France, Greece, Hungary, Portugal, Slovenia, and Spain), examining general trends, the availability of solutions, and key difficulties. Additionally, it evaluates the needs and use cases of end users and stakeholders, highlighting the essential technical features that course catalogue software solutions should encompass. By compiling key requirements, this paper contributes towards the development of appropriate and sustainable course catalogues for Higher Education Institutions.

Among the different types of applications within the realm of learning analytics, predictors and early warning systems are particularly interesting thanks to their ability to identify potentially struggling students at an early stage of a course. This paper presents a performance comparison of different classification algorithms that aim to predict whether students will pass or fail a course, using only LMS activity data from its first few weeks. Two different time frames are considered: first, using exclusively data generated before any assessment activities are performed in the course; and second, allowing the use of data originating within the time period up to, but not including, the second partial exam of the course. The study targets a first-year engineering course at the University of Vigo. In the first scenario, the tested classifiers struggled to correctly identify passing students, an issue that is mitigated in the second scenario. The main hindrance to the classifiers' performance, particularly in the first analyzed scenario, is working with a set of unbalanced data in which the number of students who pass the course is extremely low compared to those who fail.

This Research Work-in-Progress focuses on how students make use of supporting videos provided in a flipped classroom context. More specifically, this study analyzes the academic implications of the timing of video accesses: late (during the few days preceding an exam) or early. The experiment was performed in a first-year engineering course. The course is divided into 6 splits, ranging from 2 to 4 weeks each. Every split introduces new videos and ends with an exam. Data from 90 first-year students were collected. Two main analysis tasks were undertaken: assessing the correlation between the number of videos accessed early or late and exam scores, and student clustering depending on the general timing of video accesses. Significant correlation between early accesses and exam scores was only observed on the first split. Also in this first split, 3 student groups were identified via clustering: low activity, mostly late and mostly early. Interestingly, there were significant differences in long-term performance between these groups. This is a valuable result towards the development of an early warning system, as it helps identify students at risk at a early stage.

In learning analytics applications, some of the most important data sources often include the activity of students in online platforms such as learning management systems. While the utility of logs extracted from these kinds of systems is undeniable, it is important to be aware that there may be contextual factors that can change how these data is interpreted. The study showcased in this paper analyzes the direct influence between the activity volume of students in a course, as given by Moodle LMS logs, and academic performance, in the form of the final grade obtained. Moreover, we perform separate observations of this influence depending on whether the student is enrolled in the course for the first time, or if they are retaking it after failing to pass in previous academic years. The results show that a correlation exists between raw volume of interactions with the LMS and final grade, but only for first-time students. This correlation is nonexistent when considering retaking students.

This Research-to-Practice Work in Progress addresses the need for predictors in educational environments to make reliable predictions of student performance as early as possible. This is the main foundation of early warning systems, tools that aim to detect students at risk of failing or dropping out of a course, and do so at a point in time at which it is still possible to execute effective interventions to help these students. This study, carried out in the context of a first-year university course, presents a classifier of students depending on whether they are expecting to pass or fail the course, using exclusively data available before any assessment activities are performed. This classifier is based on the Random Forest algorithm. The obtained results, while limited by the scarcity of data, show promise that it is indeed possible to detect students at risk of failing with acceptable reliability in the studied educational context.

This paper details the most recent developments that were performed in the online platform BeA (Blended e-Assessment) in order to increase its usefulness and utility within the new prominent learning contexts that appeared in the year 2020 as a consequence of the COVID-19 pandemic. Due to safety recommendations such as social distancing, in-person exams need to be performed under strict restrictions, and remote exams have increased in popularity as a way to evaluate students without them leaving their home. The new BeA features allow students to directly upload pictures of their answers to the platform, circumventing the need for the exams to be scanned by the teacher. This both minimizes physical contact during in-person exams and allows students to submit their answers from home in remote exams. These new features were tested during remote exams in the 2019/2020 academic year, garnering an overall positive reception by students.

This paper presents a new module for the BeA (Blended e-Assessment) platform, aimed to be used in a higher education subject that combines the flipped classroom system and gamification features. Currently, this subject implements the flipped classroom methodology as well as intensive continuous assessment. Under this system, students are asked to watch videos that explain course contents, doing so as homework on a weekly basis. Then, students undertake an exam in the classroom covering the corresponding week's contents, counting towards the final grade of the subject. In a new approach, we decided to have students take exams every two weeks instead. However, this creates the need of maintaining a high level of student engagement, in order for them to keep watching the videos every single week. That is why we are developing a tool that allows us to apply gamification on days when students are not assessed. This tool consists of an online question system (as a multi-choice test) accessible through a web browser, which students can answer while being involved in a game.

The participation of students in the form of questions to be answered in the classroom is a key activity of the flipped classroom methodology. Those questions arise when the students watch educational videos out of the classroom (another key part of the aforementioned methodology). However, low student participation is a common problem within a flipped classroom setting. As a solution to this problem, and in order to encourage the active participation of students making questions, we are developing a system with which students can anonymously ask questions about the content of the videos, which will be later answered in class by the teacher.

This Research to Practice Work in Progress presents an analytics add-on for QMSFC (Question Management System for Flipped Classroom), an online tool with the purpose of increasing student engagement and participation in a flipped classroom setting. This is done by providing an interface that students can use to post questions about educational videos, which would then be answered by the teacher in the classroom. The data generated by QMSFC could be collected and used to expand upon the functionalities of the platform, such as alerting the teacher about particularly tough topics for students. Additionally, these data could be analyzed together with student grades in order to find out the correlation between the volume of activity on the platform and exam performance. Work remaining on this project involves using the fully developed tool in a real learning situation and analyzing the results and feedback obtained.