Browsing by Author "Maldonado Mahauad, Jorge Javier"

Now showing 1 - 20 of 58

A MOOC-based flipped experience: scaffolding SRL strategies improves learners’ time management and engagement
(2021) Pérez Sanagustín, María del Mar; Sapunar Opazo, Diego; Pérez Álvarez, Ronald Antonio; Hilleger, Isabel; Bey, Anis; Maldonado Mahauad, Jorge Javier; Baier, Jorge
Higher education institutions are increasingly considering the use of a form of blended learning, commonly named as flipped classroom (FC), in which students watch video lectures drawn from a massive online open course (MOOC) before a face-to-face lecture. This methodology is attractive, as it allows institutions to reuse high-quality material developed for MOOCs, while increasing learning flexibility and the students’ autonomy. However, the adoption of this methodology is low in general, especially in Engineering courses, as its implementation faces a number of challenges for students. The most salient challenge is the lack of student self-regulatory skills, which may result in frustration and low performance. In this paper, we study how a self-regulatory learning technological scaffold, which provides students with feedback about their activity in the MOOC, affects the engagement and performance of students in an Engineering course following a MOOC-based FC approach. To this end, we design an observational study with the participation of 242 students: 133 students in the experimental group (EG) who used a technological scaffold and 109 in the control group (CG) who did not. We did not find a statistically significant difference between the academic achievements of both groups. However, the EG exhibited a statistically significant greater engagement with the course and a more accurate strategic planning than the CG. The main implications for scaffolding self-regulated learning in FC derived from these results are discussed.
Adaptation of a process mining methodology to analyse learning strategies in a synchronous massive open online course
(Springer Science and Business Media Deutschland GmbH, 2022) Maldonado Mahauad, Jorge Javier; Pérez Sanagustín, Mar; Delgado Kloos, Carlos; Alario Hoyos, Carlos
The study of learners’ behaviour in Massive Open Online Courses (MOOCs) is a topic of great interest for the Learning Analytics (LA) research community. In the past years, there has been a special focus on the analysis of students’ learning strategies, as these have been associated with successful academic achievement. Different methods and techniques, such as temporal analysis and process mining (PM), have been applied for analysing learners’ trace data and categorising them according to their actual behaviour in a particular learning context. However, prior research in Learning Sciences and Psychology has observed that results from studies conducted in one context do not necessarily transfer or generalise to others. In this sense, there is an increasing interest in the LA community in replicating and adapting studies across contexts. This paper serves to continue this trend of reproducibility and builds upon a previous study which proposed and evaluated a PM methodology for classifying learners according to seven different behavioural patterns in three asynchronous MOOCs of Coursera. In the present study, the same methodology was applied to a synchronous MOOC on edX with N = 50,776 learners. As a result, twelve different behavioural patterns were detected. Then, we discuss what decision other researchers should made to adapt this methodology and how these decisions can have an effect on the analysis of trace data. Finally, the results obtained from applying the methodology contribute to gain insights on the study of learning strategies, providing evidence about the importance of the learning context in MOOCs
Analysis framework for tailored selection of learning objects methodologies
(INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS INC., 2015-06-01) Maldonado Mahauad, Jorge Javier
This article described the process used for developing and validating an analysis framework that allows comparing design methodologies for the design creation of Learning Objects (LO) and selecting the one that best meets the needs of teachers based on the needs of a specific educational context. This framework is called MASMDOA (Analysis Framework for the Selection of a Learning Object Design and Deployment Methodology), and it has been applied to a case study where, from a compilation of LO design methodologies used in Ibero-America, one of these methodologies is selected to work in the context of a LO design and production workshop. MASMDOA proved useful for selecting a LO design and deployment methodology that is appropriate for the requirements of an educator in a specific context. To achieve this, MASMDOA proposes a set of criteria that are useful for recommending and characterizing the methodologies to be analyzed and, following a two-phase process, it recommends the methodology that is better suited for the educator's needs. In this paper, we present MASMDOA, the case study to which it was applied, and the results obtained.
Analyzing learners’ behavior beyond the MOOC: an exploratory study
(2019) Pérez Sanagustín, María del Mar; Sharma, Kshitij; Pérez Álvarez, Ronald; Maldonado Mahauad, Jorge Javier; Broisin, Julien
Most of literature on massive open online courses (MOOCs) have focused on describing and predicting learner’s behavior with course trace data. However, little is known on the external resources beyond the MOOC they use to shape their learning experience, and how these interactions relate with their success in the course. This paper presents the results of an exploratory study that analyzes data from 572 learners in 4 MOOCs to understand (1) what the learners’ activities beyond the MOOC are, and (2) how they relate with their course performance. We analyzed frequencies of the students’ individual activities in and beyond the MOOC, and the transitions between these activities. Then, we analyzed the time spent on outside the MOOC content as well as the nature of this content. Finally, we predict which transitions better predict final learners’ grades. The results show that we can predict accurately students’ grades of the course using only internal-course fine-grained data of student’s interactions with video-lectures and exams combined with trace data of interactions with content outside the MOOCs. Also, data shows that learners spent 75% of their time on the MOOC, but go frequently to other content, mainly social networking sites, mail boxes and search engines.
Analyzing students’ behavior in a MOOC course: a process-oriented approach
(Springer Verlag, 2020) Bernal, Franklin; Maldonado Mahauad, Jorge Javier; Zúñiga Prieto, Miguel Ángel; Veintimilla Reyes, Jaime Eduardo; Mejía Pesántez, Piedad Magali; Villalba Condori, Klinge
Massive Open Online Courses (MOOCs), are one of the most disruptive trends along the last 12 years. This is evidenced by the number of students enrolled since their emergence with over 101 million people taking one of the more than 11,400 MOOCs available. However, the approval rate of students in these types of courses is only about 5%. This has led to a great deal of interest among researchers in studying students’ behavior in these types of courses. The aim of this article is to explore the behavior of students in a MOOC. Specifically, to study students learning sequences and extract their behavioral patterns in the different study sessions. To reach the goal, using process mining techniques, process models of N = 1,550 students enrolled in a MOOC in Coursera were obtained. As a result, two groups of students were classified according to their study sessions, where differences were found both in the students’ interactions with the MOOC resources and in the way the lessons were approached on a weekly basis. In addition, students who passed the course repeated the assessments several times until they passed, without returning to review a video-lecture in advance. The results of this work contribute to extend the knowledge about students’ behavior in online environments.
Assessing a methodological proposal for the design, creation and evaluation of learning objects oriented to educators with diverse educational and technological competencies
(2016) Maldonado Mahauad, Jorge Javier; Bermeo Conto, Jorge Luis; Pacheco Salazar, Vicente Guillermo
Backpack process model (Bppm). A process mining approach for curricular analytics
(2021) Sepúlveda, Marcos; Maldonado Mahauad, Jorge Javier; Salazar Fernandez, Juan Pablo; Munoz Gama, Jorge; Bustamante, Diego
Curricular analytics is the area of learning analytics that looks for insights and evidence on the relationship between curricular elements and the degree of achievement of curricular outcomes. For higher education institutions, curricular analytics can be useful for identifying the strengths and weaknesses of the curricula and for justifying changes in learning pathways for students. This work presents the study of curricular trajectories as processes (i.e., sequence of events) using process mining techniques. Specifically, the Backpack Process Model (BPPM) is defined as a novel model to unveil student trajectories, not by the courses that they take, but according to the courses that they have failed and have yet to pass. The usefulness of the proposed model is validated through the analysis of the curricular trajectories of N = 4466 engineering students considering the first courses in their program. We found differences between backpack trajectories that resulted in retention or in dropout; specific courses in the backpack and a larger initial backpack sizes were associated with a higher proportion of dropout. BPPM can contribute to understanding how students handle failed courses they must retake, providing information that could contribute to designing and implementing timely interventions in higher education institutions.
Building Institutional Capacity for Learning Analytics: Top-Down & Bottom-Up Initiatives
(2022) Perez Alvarez, Ronald; Pérez Sanagustín, Mar; Hilliger, Isabel; Maldonado Mahauad, Jorge Javier
Capacity building for Learning Analytics (LA) in Higher Education Institutions requires the coordination of organizational aspects and infrastructure development. This also depends on the organizational maturity of the institution and its leadership regarding LA adoption. LA capacity building can follow two approaches: (1) top-down, led by institutional managers; and (2) bottom-up, led by ground-level staff. This article studies two LA initiatives of each type conducted in the same institution to compare the deployment of organizational processes and infrastructure. The lessons learned that were captured from each approach are shared to inform other universities in Latin America on developing LA capabilities.
Can feedback based on predictive data improve learners' passing rates in MOOCs? a preliminary analysis
(Association for Computing Machinery, 2021) Pérez Sanagustín, María del Mar; Pérez Álvarez, Ronald Antonio; Maldonado Mahauad, Jorge Javier; Villalobos, Esteban; Hilleger, Isabel; Hernández Correa, Josefina; Sapunar, Diego; Moreno Marcos, Pedro Manuel; Muñoz Merino, Pedro; Delgado Kloos, Carlos; Imaz, Jon
This work in progress paper investigates if timely feedback increases learners’ passing rate in a MOOC. An experiment conducted with 2,421 learners in the Coursera platform tests if weekly messages sent to groups of learners with the same probability of dropping out the course can improve retention. These messages can contain information about: (1) the average time spent in the course, or (2) the average time per learning session, or (3) the exercises performed, or (4) the video-lectures completed. Preliminary results show that the completion rate increased 12% with the intervention compared with data from 1,445 learners that participated in the same course in a previous session without the intervention. We discuss the limitations of these preliminary results and the future research derived from them.
Characterizing learners' engagement in MOOCs: an observational case study using the notemyprogress tool for supporting self-regulation
(2020) Pérez Álvarez, Ronald Antonio; Maldonado Mahauad, Jorge Javier; Sharma, Kshitij; Sapunar Opazo, Diego; Pérez Sanagustín, María del Mar
IEEE Recent research shows that learners who are able to self-regulate their learning show greater levels of engagement with Massive Open Online Course (MOOC) content. To improve support for learners in their self-regulatory processes, researchers have proposed technological solutions to transform recorded MOOC data into actionable knowledge. However, studies providing empirical evidence on how these solutions impact learners' engagement with the course and their self-regulatory behavior remain scarce. In this paper, we present the results of an observational case study in which NoteMyProgress (NMP), a web-based tool designed to support learners' self-regulation in MOOCs, is applied as an intervention in two MOOCs. The main aim of this study is to provide insights into how the support of learners' Self-regulated Learning (SRL) strategies correlates with course engagement. We performed the evaluation using a sample of 263 learners and utilized distinct data sources in order to propose indicators for learners' engagement with the course and NMP. Results show a positive correlation between learners' final grades with NMP functionalities that support goal setting, organization (note-taking), and self-reflection (social comparison) SRL strategies. Furthermore, we found no significant behavioral differences in how learners with low SRL and high SRL profiles engage with the course or NMP. Finally, we discuss how these results relate to prior work and the implications for future technological solutions that seek to promote engagement in MOOCs.
Desarrollo de un plugin de recomendaciones tipo chatbot orientado a estudiantes para la plataforma Moodle
(Universidad de Cuenca, 2022-05-31) Calle Morales, Darwin Mauricio; Narváez Miranda, Edwin David; Maldonado Mahauad, Jorge Javier
Face-to-face learning is the educational model that has lasted the longest in the history of mankind, however, the emergence and use of virtual spaces such as education platforms or learning spaces have increased in recent years. These platforms, known as learning management systems, bring several benefits, such as ease of access, availability and, as a consequence, the storage of large amounts of data regarding student interactions. Data alone do not provide the expected information, that is why by processing and generating indicators it is possible to improve and understand the learning process of students. In this context appears Moodle, which is a very popular learning management system that offers the possibility of creating courses in virtual mode for free, it is also characterized by collecting and storing a large amount of data on student interactions and by creating plugins to add more functionality to the platform. Moodle has a repository of plugins, most of them are free and open source, however, in the literature reviewed there is no plugin that recommends concrete actions or strategies to improve the learning process. Similarly, in this review there are no plugins that employ novel technologies such as chatbots or conversational agents, which are already being used in different industries as interactive sources of information with high availability and that curiously in education have not been sufficiently explored. That is why, in this degree work we present the development of Miranda, a chatbot-like recommendation plugin oriented to students. The proposed tool helps students in the self-regulation of their learning, providing recommendations of time and sessions, resources and actions within the Moodle platform. Also, with the development of this chatbot plugin we try to fill the technological gap regarding the use of these technologies in the Moodle platform. Miranda's development demonstrates that it is possible to deploy a chatbot plugin that provides various recommendations to students using both Moodle-generated and Moodle-generated learning analytics indicators.
Desarrollo de un Sistema Recomendador para la Asignación de Docentes para asignaturas en la Universidad de Cuenca
(Universidad de Cuenca, 2025-09-24) Quito Urgilés, Pablo Esteban; Valdiviezo Armijos, Juan Javier; Maldonado Mahauad, Jorge Javier
The proper allocation of faculty to courses in higher education represents a key challenge in academic talent management, as it directly affects the quality of the teaching–learning process. Currently, this procedure is often carried out manually, introducing limitations such as subjectivity, lack of standardization, and high administrative workload, which frequently lead to suboptimal assignments. To address this issue, the present study proposes and va- lidates a recommender system designed to optimize the faculty assignment process. The system combines sentiment analysis, through transformer-based language models adapted to the local context, with mathematical models that enable precise alignment between faculty competencies and the specific academic requirements of each course. Faculty profiles were generated by integrating historical evaluations, automatically categorized student feedback, and competencies defined by the institutional Faculty Competency Pentagon. In addition, dynamic weights were incorporated to adjust the relevance of factors according to the aca- demic term, ensuring consistency with institutional expectations. The results demonstrate that the system met the proposed objectives, producing assignments consistent with the cri- teria of program directors in the faculty of engineering. A pilot evaluation with three directors revealed high acceptance and positive assessments of the proposed profiles and assign- ments. Although the limitations of the pilot study prevent broad generalization, the feedback suggests significant potential for application in similar contexts. Overall, the system reduces operational workload and positions itself as a strategic tool with scalability and applicability to other educational environments.
Desarrollo de un XBlock en Open edX para apoyar las analíticas de aprendizaje
(Universidad de Cuenca, 2022-07-26) Campoberde Ávila, Jonnathan Henry; Macías Narváez, Miguel Ángel; Maldonado Mahauad, Jorge Javier
Nowadays, when users use information systems, they generate a large amount of data that leaves a trace as a result of their interaction, for example, when students access educational materials in Virtual Learning Environments (VLE). This has evolved into what we now know as Massive Open Online Courses (MOOC), which have millions of students registered. Due to the large amount of data generated within MOOC, Learning Analytics (LA) has emerged as an alternative to improve teaching and learning processes through data analysis. Open edX in an attempt to incorporate LA into its Insights development platform, which provides very simple visualizations. Similarly, other projects have been added that have become obsolete over time or do not provide sufficient support to improve the student learning process. Due to the above, this degree work proposes the design, development and evaluation of a learning analytics dashboard for the Open edX platform. The tool will incorporate indicators of academic success in its visualizations to improve the learning process within the platform. With the purpose of developing the LA tool, an exploratory analysis of student behavior was carried out to determine variables and learning sequences, visualizations were designed to be incorporated into the dashboard of teachers and students. To carry out the development of the LA component, called XLEA (XBlock for LEarning Analytics), the LATUX (Learning Awareness Tool – User eXperience) methodology was used, which consists of five stages grouped into two approaches. Finally, after having evaluated the XLEA tool with the Evaluation Framework for Learning Analytics (EFLA) questionnaire and with the UEQ user experience questionnaire, by students and teachers of the University of Cuenca, a high degree of acceptance and conformity was evidenced. by participants when using XLEA. Most of the participants focused on those visualizations that allow an understanding of the historical behavior for weeks of the different activities that they carry out within the course, for example, videos, readings and problems
Descubrimiento de patrones de interacción en cursos MOOC en entornos ONLINE: un enfoque utilizando minería de procesos. Caso de estudio: “Curso de la metodología DICREVOA en Open edX”
(2016) Palta Morocho, René Andrés; Vázquez Mendoza, Jorge Alberto; Maldonado Mahauad, Jorge Javier; Bermeo Conto, Jorge Luis
Massive Open Online Courses (MOOC) open the opportunity for students around the world to access to high quality content, timeless and flexible. However, many people who enroll in a MOOC fail to finish. This is because, on the one hand, studying in these online environments requires students are able to self-regulate effectively for their learning. On the other hand, current MOOC platforms do not provide enough support for students to achieve finish the courses. In a MOOC, where the heterogeneity of the participants is a constant, self-regulated learning it is key to successfully complete them. But not all students effectively use the various self-regulatory strategies during their learning process. To this is added, the individual preference of each student to learn, that is, their learning style. The aim of this study is to explore the sequence of activities that the participants in a MOOC and determine differences in the sequences of activities among participants with different levels of self-regulation and different learning styles. To achieve this, in this study the logs are analyzed with traces of data from a MOOC course and using process mining techniques combined with self-reports, sequence patterns of student activities are extracted. The findings show that participants with different self-regulatory profiles perform sequences similar but with different intensity, while participants with different learning styles perform sequences different of activities when moving in a MOOC. These results may serve to support future decisions regarding the design of the course and platform.
Design of a Tool to Support Self-Regulated Learning Strategies in MOOCs
(2018) Pérez Álvarez, Ronald; Maldonado Mahauad, Jorge Javier; Pérez Sanagustín, Mar
The massive and open nature of MOOCs contribute to attracting a great diversity of learners. However, the learners who enroll in these types of courses have trouble achieving their course objectives. One reason for this is that they do not adequately self-regulate their learning. In this context, there are few tools to support these strategies in online learning environment. Also, the lack of metrics to evaluate the impact of the proposed tools makes it difficult to identify the key features of this type of tools. In this paper, we present the process for designing NoteMyProgress, a web application that complements a MOOC platform and supports self-regulated learning strategies. For designing NoteMyProgress we followed the Design Based Research methodology. For the evaluation of the tool, we conducted two case studies using a beta version of NoteMyProgress over three MOOCs offered in Coursera. The findings of these …
Designing a moodle plugin for promoting learners’ self-regulated learning in blended learning
(Springer Science and Business Media Deutschland GmbH, 2022) Pérez Álvarez, Ronald Antonio; Sanza, Cédric; Villalobos, Esteban; Maldonado Mahauad, Jorge Javier; Pérez Sanagustín, Mar
After the COVID-19 pandemic, universities moved towards online and Blended Learning (BL) modes to offer greater curricular flexibility. Yet, recent research shows that students have difficulties regulating their learning strategies to adapt to the different learning modes that BL entails, which mixes face-to-face with online activities taking place in different learning contexts and environments. Prior work on Self-Regulated Learning (SRL) has explored the use of dashboard-based scaffolds for supporting students’ learning strategies. However, most existing solutions are designed for supporting students in online settings (i.e., MOOCs), disregarding the teachers’ role in BL settings and the support they need to monitor and promote students’ SRL. This paper presents the design process followed for transforming a tool designed for supporting students’ SRL in MOOCs into a Moodle plugin for BL. Following a design-based research methodological approach, we describe all the phases conducted for identifying the most appropriate indicators and visualizations for supporting SRL in BL practices, implementing and evaluating a first prototype. Results of a local evaluation with 114 teachers and a broad evaluation with 311 students shed some light on the type of indicators, dashboards and functionalities that should be considered when designing solutions for supporting SRL in BL settings
Detección de secuencias de aprendizaje en cursos abiertos masivos y en línea
(2019-10-24) Bernal Montenegro, Franklin Bolívar; Maldonado Mahauad, Jorge Javier
The use of technology in current educational contexts, for example, face-to-face, mixed and online have changed the way of teaching and learning. In these contexts, the massive and online open courses (MOOCs) are one of the most disruptive trends of the last 8 years, with approximately 101 million people enrolled in some of the more than 11,400 MOOCs offered by some of 2012-2018 The right platforms such as Coursera. However, the approval rate of students in these types of courses barely borders 5%. This has caused a great interest in researchers to study the behavior of students in this type of courses; and also the power to reveal why a student ends or not a MOOC. The objective of this thesis work is to explore the behavior of students in a MOOC course. Specifically, it seeks to study the learning sequences and extract the behavior patterns in the study sessions they perform in a MOOC, and the relationship with their academic performance. To achieve the objective proposed in this work, make use of machine learning and process mining techniques, obtain records of events that allow modeling the behavior of students in a MOOC course on the Coursera platform (N = 1,550). This event log allows you to extract the characteristics of the students' study sessions and to demonstrate the interactions of the students with the resources of the course for each week of the course. As a result, we obtained two groups of students identified in their study sessions, where we found statistically specific differences between the study sessions of both groups. In addition, differences were found between student interactions with MOOC resources and how to address the lessons per week between both groups. The results found according to the characterization of the students of a MOOC based on their study sessions. In addition, intense behavior was identified by the students who passed the course, in which he repeated the evaluations several times until he was able to pass them, without returning to a previous activity video-reading, that is; the students were persevering and repeated the evaluations until they were approved.
Detection of learning strategies: a comparison of process, sequence and network analytic approaches
(Springer Link, 2019) Pérez Sanagustín, Mar; Matcha, Wannisa; Gasevic, Dragan; Ahmad Uzir, Noraayu; Jovanovic, Jelena; Pardo, Abelardo; Maldonado Mahauad, Jorge Javier
© 2019, Springer Nature Switzerland AG. Research in learning analytics proposed different computational techniques to detect learning tactics and strategies adopted by learners in digital environments through the analysis of students’ trace data. While many promising insights have been produced, there has been much less understanding about how and to what extent different data analytic approaches influence results. This paper presents a comparison of three analytic approaches including process, sequence, and network approaches for detection of learning tactics and strategies. The analysis was performed on a dataset collected in a massive open online course on software programming. All three approaches produced four tactics and three strategy groups. The tactics detected by using the sequence analysis approach differed from those identified by the other two methods. The process and network analytic approaches had more than 66% of similarity in the detected tactics. Learning strategies detected by the three approaches proved to be highly similar.
DICREVOA: A proposal for the design, creation and evaluation of learning objects
(IEEE, 2015) Maldonado Mahauad, Jorge Javier; Bermeo Conto, Jorge Luis; Mejía Pesántez, Piedad Magali; Mejía Pesántez, Piedad Magali
This article describes a methodological proposal for the design, creation and evaluation of Learning Objects (LO). This work arises from the compilation and analysis of several LO design methodologies currently used in Ibero-America. This proposal, which has been named DICREVOA, defines five different phases: analysis, design (instructional and multimedia), implementation (LO and metadata), evaluation (from the perspective of the LO producer and consumer) and publication. The methodology is focused not only on the teaching inexperienced but also on those having a basic understanding of the technological and educational aspects related to the design of LO, therefore, the proposal emphasizes LO design activities centered in the Kolb cycle and the use of the ExeLearning tool in order to implement the LO core. Additionally, DICREVOA was used in a study case, which demonstrates how it provides a viable mechanism for the LO design and implementation within different contexts. In this paper, we present DICREVOA, the case study to wich it was applied, and the obtained results
Diseño de un centro de datos basado en estándares. Caso práctico: diseño del centro de datos del colegio Latinoamericano
(2010) Maldonado Mahauad, Jorge Javier; Parra González, Luis Otto