Peer and self-assessment are widely recognized as effective strategies for fostering critical thinking, reflective learning, and the development of professional skills in educational contexts. These approaches enable students to actively participate in the learning process by evaluating their own work and that of their peers. Despite their potential benefits, traditional assessment methods often encounter significant challenges, such as inconsistent feedback quality, limited student engagement, and a lack of actionable insights that students can use to improve their performance. Addressing these limitations, this paper introduces AICoFe (“Artificial Intelligence-based Collaborative Feedback system”), an innovative platform designed to enhance the feedback process through the integration of generative artificial intelligence (GenAI) and Learning Analytics dashboards. AICoFe facilitates both peer and self-assessments using rubric-based frameworks that combine quantitative scores with qualitative observations. By leveraging GenAI, through an adapted version of GePeTo, the system provides personalized, actionable feedback tailored to individual student performance. This feedback is displayed on Learning Analytics dashboards, which also allow students to compare their performance against peers and reflect on their results through comparative graphs. Additionally, AICoFe includes video recordings of student performances to promote self-reflection and a deeper understanding of strengths and areas for improvement. These functionalities enable students to engage more effectively with the provided feedback, fostering continuous learning and development. The system's effectiveness was evaluated through a case study involving final-year engineering students tasked with improving their oral presentation skills. A customized rubric was designed to assess various aspects of effective presentations. Preliminary findings demonstrated that the feedback provided by AICoFe was perceived as clear, specific, and actionable. The study underscores the transformative potential of combining AI-driven feedback with dynamic visualization tools to create a holistic and engaging assessment process. Future work will explore additional features, such as advanced video and audio analysis, and expand the system's application to other skill areas, solidifying its role as a versatile tool for modern educational needs.

The widespread adoption of Massive Open Online Courses (MOOCs) has profoundly influenced higher education by granting learners access to an extensive array of educational materials. However, the substantial volume of data generated by MOOCs presents a considerable challenge for instructors who aim to assess and facilitate effective learner support. In this study, we introduce an innovative GenAI-based (Generative Artificial Intelligence) tool designed to assist and guide MOOC learners in understanding their progress in the course to enhance their performance and prevent dropout. Our proposed approach takes advantage of GenAI's capabilities to analyze and understand anonymized learner educational data, including aspects such as course progression, assignment results, time spent on different types of content, timestamps, and other pertinent information. By applying natural language processing techniques, GenAI identifies patterns and trends within the data, enabling it to provide personalized guidance to learners to help them develop better learning strategies and enhance their performance in the course. The proposed tool, named GePeTo (Generative AI-based Personalized Guidance Tool), not only streamlines the process of analyzing large volumes of educational data but also equips instructors with practical insights into their learners' performance and difficulties. GePeTo offers a promising solution for higher education institutions aiming to leverage the potential of MOOC data for effective learner assessment and support. Automating the analysis of educational data and delivering personalized guidance to learners will also facilitate instructors in making data-driven decisions. Ultimately, this will improve learning outcomes and educational experiences for learners in the digital age of education.

In this article, we present a Web-based System called M2LADS, which supports the integration and visualization of multimodal data recorded in learning sessions in a MOOC in the form of Web-based Dashboards. Based on the edBB platform, the multimodal data gathered contains biometric and behavioral signals including electroencephalogram data to measure learners’ cognitive attention, heart rate for affective measures, visual attention from the video recordings. Additionally, learners’ static background data and their learning performance measures are tracked using LOGCE and MOOC tracking logs respectively, and both are included in the Web-based System. M2LADS provides opportunities to capture learners’ holistic experience during their interactions with the MOOC, which can in turn be used to improve their learning outcomes through feedback visualizations and interventions, as well as to enhance learning analytics models and improve the open content of the MOOC.

Recognition of learning techniques such as badges and micro credentials are broadly used in education. Both LMSs and MOOCs incorporate these techniques to inform learners of their achievements. This meta-review study aims to provide an overview of recognition of learning in both LMSs and MOOCs, by gathering previous literature reviews and overview studies in this field. The studies reviewed show multiple applications, mainly using badges and gamification in MOOCs. Results of the studies have been broadly positive and, together with the recommendations and lessons learned in previous research, encourage the future research in recognition of learning.

The main objective of this research is to propose a student-centered learning platform called ERC (English Reading Comprehension)-Language, for the developing of textual and topic-based knowledge. The proposed platform facilitates literal reading comprehension processes, the construction of linguistic and thematic knowledge, and improves students' reading performance. With the purpose to know the students' perceptions about the implementation of the ERC-Language platform, a perception study was performed. In this study 18 students of the Electronic Engineering bachelor program, from Universidad Pontificia Bolivariana (UPB Monteria Sectional) participated. The main results let us corroborate the necessity to develop a student-centered learning platform to improve non-native' ERC skills.

Nowadays, there is a great variety of approaches aimed at facilitating the effectiveness of the teaching and learning processes. Many of those approaches are based on specific Educational Technologies whose objective is to make the teaching and learning experiences as human as possible. Tools and techniques for the recognition and analysis of emotions in online courses, such as those for the adaptations and the personalization of these courses, are some examples of the aforementioned approaches. At UAM we have designed and developed a tool for extracting and analysing the emotions of our online courses, such as SPOCs and MOOCs. We call this tool edX-CAS, which is the acronym for “Content Analyser System for edX MOOCs”. In this paper, a detailed description of this Tool is presented and an interesting description of current research work in the area of Polarity analysis, Sentiment analysis or Opinion mining in online courses is explained.

Computational thinking is a necessary skill for human life. However, promoting this competency in primary school students sometimes is hard and difficult for instructors. This article proposes a learning approach based on the use of a platform as part of a strategy of computational thinking to enhance learning of geometry. A case study was performed with primary school children from fourth grade at the Comfacor School (Montería-Colombia). The aim of the study was to analyze the effects of the approach in the children's motivation and performance.

The massive quantity of learners generating information related to Massive Open Online Courses (MOOCs) make researchers analyze large datasets about the learners' profile, interaction, satisfaction, etc. and these datasets can come from multiple data sources related to the same or different courses. This paper details the conducted exploratory analysis performed with data from two different MOOCs of different knowledge areas to check the factors that influence the learners' retention and certification. The preliminary results we obtained allow us to provide some conclusions with the aim to keep researching in order to generalize our achievements.

In this paper a learning analytics dashboard for MOOCs is proposed. It visualises the progress of learners' activity taking into account navigation, social interactions and interaction with educational resources. This approach was tested with the MOOCs created by the University Autonóma of Madrid (Spain) in the edX platform. Nowadays, the dashboard is being improved taking into account the received feedback from MOOCs instructors and assistants. Finally, a new version is presented to work along with edX and Open edX.

The main purpose of this paper is to present the made improvements to an innovative tool called Assessment Manager. These improvements are related with the implementation of analytic rubrics to help the instructors in the design of the assessment from the collaborative learning process completed by the students into Learning Management System courses. The assessment tool is part of a Teaching Assistant Service embedded into the Learning Management System Moodle. This assistant together with the assessment tool are being used and tested in several courses to support Computer Science Engineering Education. The tests are being performed as innovative educational practices with instructors and students members from the Faculty of Computer Science Engineering at the Universidad Pontificia Bolivariana-UPB Montería and members from the School of Computer Science Engineering at the Universidad del Valle-UNIVALLE Santiago de Cali (Colombia).

The MOOCs offers technologies which emerge as an alternative to support the blending of face-to-face pedagogies and virtual activities. However, a blended learning experience is influenced by several factors, such as: the student's attitude to learn; a well-known learning script; and interactions and group dynamic. This article proposes MOOCs scenarios based on the experience of two collaborative approaches implemented by the authors. These experiences are gathered in three aspects: methodological; technological; and educational practice. In conclusion, this article highlights a lack of services related with social interaction, monitoring and intervention by the instructors; without such services, the MOOCs technologies hardly support blended learning experiences.

The main purpose of this paper is to present an awareness information service called Notification Manager. The implementation of the manager is embedded into the Learning Management System Moodle. The aim of the Notification Manager is to support student-student interactions in collaborative learning tasks performed by students and instructors into the system. To test the implemented manager, an experimentation was carried out with students from the Simulation course at the Faculty of Informatics Engineering at the Universidad Pontificia Bolivariana, UPB-Montería (Colombia) in the second semester of 2013.

The effectiveness of a MOOC as a learning environment could be encouraged by an active students' participation in social and collaborative learning processes. In this sense, both social media platforms and collaborative learning services have showed several successful experiences with massive projects. However, in this context, the lack of a pedagogical model that can be coupled with a multiple media and distributed resources increases the complexity of processes such as monitoring and assessment, which are fundamental in a learning environment. In consequence, this can produce the instructors' workload when they script and perform learning activities into these scenarios. This paper presents several reflections about monitoring and assessment processes from two collaborative learning systems approaches and proposes some ideas about their application in a MOOC context, with the aim to reduce the instructors' workload. Additionally, other considerations about massive collaborative learning experiences are presented.

This document introduces the GHIA research group, summarizes its main research areas regarding e-Learning systems and spot out some of its future work, exposing all this information within the context of the eMadrid network.

Meta-modelling is one of the pillars of model-driven engineering (MDE), where it is used for language engineering and domain modelling. Even though the current trend is the use of two-level meta-modelling frameworks, several researchers have pointed out limitations of this scheme for some scenarios and suggested a meta-modelling approach with an arbitrary number of meta-levels in order to obtain more flexible and simpler system descriptions. Unfortunately, such multi-level meta-modelling systems are still in their infancy, lacking, for example, integration with model manipulation languages, a characterization of different possibilities for instantiation and inheritance and primitives for interconnecting multi-level languages in a flexible way. In the paper, we propose a number of extensions to multi-level (also called deep) meta-modelling, on the basis of the needs raised by its use for practical MDE. In particular, we discuss on the issues related to code generation from deep languages, the benefits of allowing inheritance at every meta-level and patterns and techniques for a fine-grain control of the meta-level of elements. Finally, we provide primitives to control the impedance mismatch when connecting models at different meta-levels.

In this work, we analyze the possible existing correlations between student marks, as assigned by their classmates or by their instructors, and the emotion traces that can be found in their writings. For that purpose, data corresponding to 168 contributions of a course on Computer Systems were gathered. The results obtained indicate that some kind of correlation exists between marks and emotions, as in the case of highest marks as at the case of lowest marks.

Multimedia resources offer an opportunity to innovate and improve teaching and learning environments through the interactivity. However, the interactivity is weakly supported by current learning environments and there is a lack of tools to build this type of material. Therefore, this paper describes a new collaborative environment for composing multimedia-interactive learning objects, called Social Media Learning (SMLearning). This environment includes a methodological guideline and a Social Media platform. This article presents details about Authoring Tool and Multimedia Player, which have been tested in a blended learning experience with a postgraduate course at the University Autónoma of Madrid, where students and teachers have been worked together for generating multimedia-interactive educational material.

The increasing popularity of Massive Open Online Courses (MOOCs) has raised the need for highly scalable, customizable, open learning environments. At the same time, there is a growing trend to open the services that the companies offer on the web with open APIs and in the form of REST services, facilitating their integration in customized applications. The goal of this work is to show how such open services can be used for the support of on-line educational systems. These services were not created for an education context, so it is necessary to complement it with functionalities for supporting aspects such as evaluations, monitoring or collaboration. This article discusses on the strategies for integrating services for education and presents two cases studies: first, SMLearning, a collaborative learning environment supported by social media platforms Facebook and YouTube, and second, an application for project-based programming courses, customized through a generative architecture, making heavy use of Google services.

The assessment of learning outcomes is a key concept in the European Credit Transfer and Accumulation System (ECTS) since credits are awarded when the assessment shows the competences which were aimed at have been developed at an appropriate level. This paper describes a study which was first part of the Bologna Experts Team-Spain project and then developed as an independent study. It was carried out with the overall goal to gain experience in the assessment of learning outcomes. More specifically it aimed at 1) designing procedures for the assessment of learning outcomes related to these compulsory generic competences; 2) testing some basic psychometric features that an assessment device with some consequences for the subjects being evaluated needs to prove; 3) testing different procedures of standard setting, and 4) using assessment results as orienting feedback to students and their tutors. The process of development of tests to carry out the assessment of learning outcomes is described as well as some basic features regarding their reliability and validity. First conclusions on the comparison of the results achieved at two academic levels are also presented.

In this work, we analyze the possible existing correlations associated to short technical documents written by graduate students between its social acceptation, which are related to assigned classmates' marks and its emotion traces. The results obtained indicate that some kind of correlation exists between quality measure and emotions in the case of classmates' highest marks.

This paper presents the results of the use of a Motivation Booster in blended learning experiences. The implementation of the booster is embedded in the KnowCat system. The main findings presented are related with the improvement of the blended learning experiences. Specifically the motivational messages sent by the Motivation Booster to the students help to increase the students' interactions in the system, when they perform collaborative learning activities without the instructor's guide. Besides, these messages influence in the students' intrinsic motivation, which is represented in their motivational factors.

In this paper, we present a questionnaire-driven collaborative design methodology for the automatic generation of collaborative applications. The methodology is based on a repository of collaborative components and a knowledge base of its application and use modes. The repository includes components

The main focus of the proposed approach in this paper is to provide to CSCL users personalized and summarized feedback on the completed collaborative learning activities. The main purpose of this approach is to improve CSCL environments through the provision of a Motivation Booster by monitoring the users´ progress in the system. The implementation of the booster is embedded in two specific systems: the Learning Management System (LMS) known as Moodle and a CSCL called KnowCat. Several research studies are performed with the aim to test both implementations of the Motivation Booster in the mentioned systems. These research studies are carried out with groups of students and teachers from the Universidad Autónoma de Madrid (Spain) and from the Universidad Pontificia Bolivariana (Monteria, Colombia).

For more than one decade knowledge management has taken advantage of some abilities that software agents are endowed with. Agent features such as autonomy, cooperation, communication, and learning capacity have been used to improve the performance of knowledge management applications. In this paper we outline our proposal for implementing a Jade-based multi-agent platform to enhance the potential of KnowCat: a fully consolidated, thoroughly tested and validated knowledge management system which has been in active use at Universidad Autonoma de Madrid (Spain) since 1998. We also give a succinct description of the agent platform architecture and a brief presentation of its current status

In open environments like the Web, and open multiagent and Peer2Peer systems, consent among the autonomous, self-interested knowledge sources and users very often cannot be established, and the estimation of trustability and truthfulness of knowledge sources may not be possible. Moreover, competing viewpoints and their communicative contexts even provide valuable meta-knowledge about the intentions of the participants and their social relationships. As a foundational approach to semantically heterogeneous knowledge perspectives, we introduce a formal framework for the computational representation and integration of multi-source knowledge, which makes explicit heterogeneous viewpoints, and conflicting opinions and their social contexts, and allows for the rating, generalization and optional fusion of knowledge by social choice.