Search

Early diagnosis of Alzheimer's disease and its prodromal stage, also known as mild cognitive impairment (MCI), is critical since some patients with progressive MCI will develop the disease. We propose a multi-stream deep convolutional neural network fed with patch-based imaging data to classify stable MCI and progressive MCI. First, we compare MRI images of Alzheimer's disease with cognitively normal subjects to identify distinct anatomical landmarks using a multivariate statistical test. These landmarks are then used to extract patches that are fed into the proposed multi-stream convolutional neural network to classify MRI images. Next, we train the architecture in a separate scenario using samples from Alzheimer's disease images, which are anatomically similar to the progressive MCI ones and cognitively normal images to compensate for the lack of progressive MCI training data. Finally, we transfer the trained model weights to the proposed architecture in order to fine-tune the model using progressive MCI and stable MCI data. Experimental results on the ADNI-1 dataset indicate that our method outperforms existing methods for MCI classification, with an F1-score of 85.96%.

Several studies have explored the factors that influence self-efficacy as well as its contribution to academic development in online learning environments in recent years. However, little research has investigated the effect of a web-based learning environment on enhancing students’ beliefs about self-efficacy for learning. This is especially noticeable in the field of online distributed programming. We need to design online learning environments for programming education that foster both students’ self-efficacy for programming learning and the added value that students perceive of the tool as a successful learning environment. To that end, we conducted a quantitative analysis to collect and analyze data of students using an online Distributed Systems Laboratory (DSLab) in an authentic, long-term online educational experience. The results indicate that (1) our distributed programming learning tool provides an environment that increases students’ belief of programming self-efficacy; (2) the students’ experience with the tool strengthens their belief in the intrinsic value of the tool; however (3) the relationship between students’ belief in the tool intrinsic value and their self-efficacy is inconclusive. This study provides relevant implications for online distributed (or general) programming course teachers who seek to increase students’ engagement, learning and performance in this field.

This paper examines the implementation of unplugged tasks across different school settings developing computational thinking skills and concepts at upper primary school children in Spain without programming and without using electronic devices. The study is based on qualitative case study design. Across the three case studies/schools – Waldorf-Steiner, conventional and innovative – several themes and key tasks were emerged for unplugged computational thinking development. The evidence stems from observation field notes and interview transcripts with 152 participants. We collected 94 lessons in total, and we analyzed the data based on a predefined coding scheme and thematic content analysis. We conclude that the detected unplugged tasks demonstrate a great potential to develop computational thinking skills and concepts, even though the teachers are not fully aware of their development. The study highlights the need for teacher professional development on computational thinking teaching and learning. Also, we stress the need for computational thinking skills, concepts, and tasks integration into curriculum explicitly. Given the paucity of research on unplugged methods and computational thinking development in primary education, this study is promising to uncover some prominent issues for further examination and future research agenda.

Artificial intelligence systems such as early warning systems are becoming more common in Higher Education. However, the students' reactions to such techno-pedagogical innovations are much less explored in settings beyond the development and testing. This paper analyses the students' acceptance of an early warning system developed at a fully online university. Following a pre-usage and post-usage experimental design based on the Unified Theory of Acceptance and Use of Technology model and the Structural Equation Modelling, we observed how, within four courses (839 participants in the academic year 2019–20, of which 347 participants answered both a pre- and post-usage questionnaire), the students' acceptance changed overtime. Our findings revealed a disconfirmation effect in the acceptance of the early warning system, namely, a difference between expectations surrounding the technology pre- and post-usage, and shed light on the ways artificial intelligence systems should be integrated within Higher Education virtual classrooms.

Paper guanyador del premi al millor article del congrés JENUI'22 (Jornadas sobre la Enseñanza Universitaria de la Informática). La Unidad de Igualdad de la Universitat Oberta de Catalunya (UOC) en su último plan de igualdad incluyó, entre otros objetivos, el de asegurar la perspectiva de género en la docencia. La vía propuesta fue la definición de una competencia transversal (Comportamiento ético y global) que debería implantarse en todos los programas. Por su parte, la Facultad de Informática de la misma universidad trabaja en el mismo sentido desde 2019 en su Comisión de Equidad. En este artículo se expone el proceso seguido desde la aparición de este impulso institucional hasta su conceptualización en dicha competencia y su vinculación concreta a un subconjunto de las asignaturas del Grado y del Máster en Ingeniería nformática. Se detallan las fases, las directrices establecidas, la selección de las asignaturas y un ejemplo de implantación en una de ellas. El principal resultado de la experiencia es que este es un proceso viable gracias a unos factores facilitadores ya existentes y a la implicación de los grupos interesados, pero que no está libre de contradicciones ni es todavía maduro en todos los aspectos clave, entre ellos algunos tan relevantes como el de la evaluación de la competencia. The last equality plan of the Gender Unit of the Universitat Oberta de Catalunya includes, among others goals, ensuring a gender perspective in the teaching process. To this aim, a new transversal competency (Global and Ethical Behaviour), that should be included in every official bachelor’s and master’s degree programme, has been defined. For its part, the Computer Science Faculty of the same university, has been working in the same direction since 2019 within its Equality Commission. In this paper, we present the process followed since the emergence of this institutional impulse to its conceptualization as a competence and its specific implementation in a subset the Bachelor's and Master's in Computer Engineering courses. The phases, the established guidelines, the selection of the subjects and an example of implementation in one of them are detailed. The main result of the experience is that this is a viable process thanks to some facilitating factors that already exist and to the involvement of the stakeholders. Even though it is not free from contradictions nor it is yet mature in all the key aspects, including some that are so relevant such as the competence evaluation.

Steganalysis is a collection of techniques used to detect whether secret information is embedded in a carrier using steganography. Most of the existing steganalytic methods are based on machine learning, which typically requires training a classifier with "laboratory" data. However, applying machine-learning classification to a new source of data is challenging, since there is typically a mismatch between the training and the testing sets. In addition, other sources of uncertainty affect the steganlytic process, including the mismatch between the targeted and the true steganographic algorithms, unknown parameters -- such as the message length -- and even having a mixture of several algorithms and parameters, which would constitute a realistic scenario. This paper presents subsequent embedding as a valuable strategy that can be incorporated into modern steganalysis. Although this solution has been applied in previous works, a theoretical basis for this strategy was missing. Here, we cover this research gap by introducing the "directionality" property of features with respect to data embedding. Once this strategy is sustained by a consistent theoretical framework, new practical applications are also described and tested against standard steganography, moving steganalysis closer to real-world conditions.

Oyster fungi Pleurotus djamor generate actin potential like spikes of electrical potential. The trains of spikes might manifest propagation of growing mycelium in a substrate, transportation of nutrients and metabolites and communication processes in the mycelium network. The spiking activity of the mycelium networks is highly variable compared to neural activity and therefore can not be analysed by standard tools from neuroscience. We propose original techniques for detecting and classifying the spiking activity of fungi. Using these techniques, we analyse the information-theoretic complexity of the fungal electrical activity. The results can pave ways for future research on sensorial fusion and decision making of fungi.

Fungal electronics is a family of living electronic devices made of mycelium bound composites or pure mycelium. Fungal electronic devices are capable of changing their impedance and generating spikes of electrical potential in response to external control parameters. Fungal electronics can be embedded into fungal materials and wearables or used as stand alone sensing and computing devices.

Retina fundus imaging; Deep learning; Medical imaging Imatge del fons de la retina; Aprenentatge profund; Imatges mèdiques Imagen del fondo de la retina; Aprendizaje profundo; Imágenes médicas Cardiovascular diseases (CVD) are one of the leading causes of death in the developed countries. Previous studies suggest that retina blood vessels provide relevant information on cardiovascular risk. Retina fundus imaging (RFI) is a cheap medical imaging test that is already regularly performed in diabetic population as screening of diabetic retinopathy (DR). Since diabetes is a major cause of CVD, we wanted to explore the use Deep Learning architectures on RFI as a tool for predicting CV risk in this population. Particularly, we use the coronary artery calcium (CAC) score as a marker, and train a convolutional neural network (CNN) to predict whether it surpasses a certain threshold defined by experts. The preliminary experiments on a reduced set of clinically verified patients show promising accuracies. In addition, we observed that elementary clinical data is positively correlated with the risk of suffering from a CV disease. We found that the results from both informational cues are complementary, and we propose two applications that can benefit from the combination of image analysis and clinical data. This research was funded by “RTI2018-095232-B-C22” grant from the Spanish Ministry of Science, Innovation and Universities (FEDER funds).

Background The preparation consisting of a head-fixed mouse on a spherical or cylindrical treadmill offers unique advantages in a variety of experimental contexts. Head fixation provides the mechanical stability necessary for optical and electrophysiological recordings and stimulation. Additionally, it can be combined with virtual environments such as T-mazes, enabling these types of recording during diverse behaviors. New method In this paper we present a low-cost, easy-to-build acquisition system, along with scalable computational methods to quantitatively measure behavior (locomotion and paws, whiskers, and tail motion patterns) in head-fixed mice locomoting on cylindrical or spherical treadmills. Existing methods Several custom supervised and unsupervised methods have been developed for measuring behavior in mice. However, to date there is no low-cost, turn-key, general-purpose, and scalable system for acquiring and quantifying behavior in mice. Results We benchmark our algorithms against ground truth data generated either by manual labeling or by simpler methods of feature extraction. We demonstrate that our algorithms achieve good performance, both in supervised and unsupervised settings. Conclusions We present a low-cost suite of tools for behavioral quantification, which serve as valuable complements to recording and stimulation technologies being developed for the head-fixed mouse preparation.

Learning to code can be considered as one of the most representative examples of learning by doing. Programming is a skill and learning skills requires practice. Online teaching and learning depend on tools that allow students practice and teachers to monitor student progress and provide feedback. In this work, the design and architecture of an educational tool for learning to code are presented. The CodeLab tool is based on skill practice and assessment and is targeted for non-STEM students to develop computational thinking and programming competences. The tool is designed to provide an educational lab experience based on activities to practice through a conversational interface.

Domain experts typically have detailed knowledge of the concepts that are used in their domain; however they often lack the technical skills needed to translate that knowledge into model-driven engineering (MDE) idioms and technologies. Flexible or bottom-up modelling has been introduced to assist with the involvement of domain experts by promoting the use of simple drawing tools. In traditional MDE the engineering process starts with the definition of a metamodel which is used for the instantiation of models. In bottom-up MDE example models are defined at the beginning, letting the domain experts and language engineers focus on expressing the concepts rather than spending time on technical details of the metamodelling infrastructure. The metamodel is then created manually or inferred automatically. The flexibility that bottom-up MDE offers comes with the cost of having nodes in the example models left untyped. As a result, concepts that might be important for the definition of the domain will be ignored while the example models cannot be adequately re-used in future iterations of the language definition process. In this paper, we propose a novel approach that assists in the inference of the types of untyped model elements using Constraint Programming. We evaluate the proposed approach in a number of example models to identify the performance of the prediction mechanism and the benefits it offers. The reduction in the effort needed to complete the missing types reaches up to 91.45% compared to the scenario where the language engineers had to identify and complete the types without guidance.

Calculus courses often present a large number of difficulties to undergraduate students of scientific studies, especially in engineering degrees. These difficulties are sometimes related to teaching and assessment strategies. In this paper, a teaching innovation experience is presented within the framework of the Universitat Oberta de Catalunya. This teaching experience is focused on a continuous assessment through a systematic use of the so-called WIRIS quizzes. Academic outcomes are very positive from both quantitative and qualitative viewpoints.

In this paper, we propose a solution to the problem of guaranteed time slot allocation in cluster-tree WSNs. Our design uses the so-called Network Utility Maximization (NUM) approach as far as we aim to provide a fair distribution of the available resources. From the point of view of implementation, we extend here the authors' proposed Coupled-Decompositions Method (CDM) in order to compute the NUM problem inside the cluster tree topology and we prove the optimality of this new extended version of the method. As a result, we obtain a distributed solution that reduces the total amount of signalling information in the network up to a factor of 500 with respect to the classical techniques, that is, primal and dual decomposition. This is possible because the CDM finds the optimal solution with a small number of iterations. Furthermore, when we compare our solution to the standard-proposed First Come First Serve (FCFS) policy, we realize that FCFS becomes pretty unfair as the traffic load in the network increases and thus, a fair allocation of resources can be considered whenever the price to pay in terms of signalling and computational complexity is controlled.

Adaptive e-learning systems are able to automatically generate personalized learning paths from the students’ profile. Generally, the student profile is updated with information about knowledge the student has acquired, courses the student has passed and previous work experience. Unfortunately, dealing with courses that students passed in other learning environments is very difficult, error prone and requires a lot of manual intervention. In addition, the recognition of external courses is a process that all institutions, on-site and online learning organization, must perform during the access of new students, since it can be greatly useful not only for personalization but also for recognizing the courses the students attended. In this paper, we propose an intelligent system that analyzes the academic record of students in textual format to identify what subjects the students studied in the past and therefore are potentially recognizable. In addition, the proposed system is able to enrich the information the institution has about the students’ background, facilitating the identification of personalized learning paths.

Technological progress in recent decades has enabled people to learn in different ways. Universities now have more educational models to choose from, i.e., b-learning and e-learning. Despite the increasing opportunities for students and instructors, online learning also brings challenges due to the absence of direct human contact. Online environments allow the generation of large amounts of data related to learning/teaching processes, which offers the possibility of extracting valuable information that may be employed to improve students’ performance. In this paper, we aim to review the similarities and differences between Educational Data Mining and Learning Analytics, two relatively new and increasingly popular fields of research concerned with the collection, analysis, and interpretation of educational data. Their origins, goals, differences, similarities, time evolution, and challenges are addressed, as are their relationship with Big Data and MOOCs., El progrés tecnològic de les darreres dècades ha fet possible una diversitat de formes d’aprenentatge. Avui dia les universitats ofereixen múltiples models d’ensenyament entre els quals podem triar, per exemple, l’aprenentatge mixt (b-learning) o l’aprenentatge electrònic. Si bé cada cop són més nombroses les oportunitats per a alumnes i professors, l’aprenentatge en línia també planteja dificultats degudes a la manca de contacte humà directe. Els entorns en línia permeten que es generin grans quantitats de dades relacionades amb els processos d’ensenyament i aprenentatge, de les quals es pot extreure una valuosa informació que es pot fer servir per millorar l’actuació de l’alumnat. En aquest treball volem estudiar les semblances i diferències entre la mineria de dades educatives i l’anàlisi de dades sobre l’aprenentatge, dos camps de recerca relativament nous i creixentment populars relacionats amb la recollida, l’anàlisi i la interpretació de dades sobre educació. En tractarem l’origen, els objectius, les diferències i semblances, l’evolució que han tingut en el temps i els reptes a què s’enfronten, així com la seva relació amb les dades massives i els cursos en línia oberts i massius (MOOC)., El progreso tecnológico de las últimas décadas ha hecho posible una diversidad de formas de aprendizaje. Hoy en día las universidades ofrecen múltiples modelos de enseñanza entre los que poder elegir, por ejemplo aprendizaje mixto (b-learning) o aprendizaje electrónico. Aunque cada vez son más numerosas las oportunidades para alumnos y profesores, el aprendizaje en línea también plantea dificultades debidas a la falta de contacto humano directo. Los entornos en línea permiten generar grandes cantidades de datos relacionados con los procesos de enseñanza-aprendizaje, de los que se puede extraer una valiosa información que se puede usar para mejorar el desempeño del alumnado. En este trabajo queremos estudiar los parecidos y diferencias entre la minería de datos educativos y el análisis de datos sobre aprendizaje, dos campos de investigación relativamente nuevos y crecientemente populares relacionados con la recogida, el análisis y la interpretación de datos educativos. Trataremos su origen, objetivos, diferencias y parecidos, evolución en el tiempo y retos a los que se enfrentan, así como su relación con los macrodatos y los cursos en línea abiertos y masivos (MOOC).

[spa] La siguiente experiencia muestra las posibilidades educativas del uso del aprendizaje móvil y de códigos QR en el aula de Educación física de secundaria como herramienta para fomentar la práctica de actividad física saludable. La experiencia ha sido diseñada en forma de unidad didáctica colaborativa para el alumnado de segundo curso de educación secundaria obligatoria de dos centros educativos de Barcelona. El objetivo principal ha sido simular el ascenso al Everest mediante la realización de retos colaborativos de fuerza resistencia diseñados por el alumnado y convertidos en códigos QR. La suma de repeticiones de fuerza conseguidas de forma colaborativa entre el alumnado de ambos centros ha simulado en metros la ascensión al Everest. La experiencia se ha basado en la investigación educativa cualitativa y bajo un diseño de casos múltiple y ha utilizado una metodología colaborativa para la consecución del reto. Los resultados obtenidos han demostrado el potencial del aprendizaje móvil como herramienta educativa emergente facilitadora y motivadora del proceso de enseñanza aprendizaje., [eng] The experience presented in this article highlights the educational potential of using mobile learning and QR codes in a secondary physical education classroom to foster healthy physical activity. The experience was designed as a collaborative didactic unit for 13/14 year-old compulsory secondary education pupils from two schools in Barcelona, Spain. The main objective was to simulate a Mount Everest ascent by performing collaborative resistance strength challenges designed by the pupils and converted into QR codes. The total number of strength exercise repetitions that the pupils from both schools managed to do collaboratively simulated the number of metres climbed towards the summit of Mount Everest. The experience was based on qualitative educational research and had a multiple case-study design. Moreover, it used a collaborative methodology to accomplish the challenge. The results obtained show the potential of mobile learning as an emergent educational tool that is capable of facilitating and fostering the teaching-learning process.

Actualmente presenciamos una etapa de importantes cambios como consecuencia de la emergencia de las tecnologías de la información y la comunicación (TIC). La educación superior ejerce un papel clave para ayudar a los estudiantes a adquirir las competencias que les permitan desenvolverse en los entornos académico y profesional. Entre éstas, las vinculadas a las TIC y los procesos de colaboración se consideran claves. La finalidad del presente estudio es analizar la percepción de los estudiantes a fin de evidenciar cómo la construcción colaborativa de un proyecto digital facilita la adquisición de las competencias digitales. Para ello, se aborda el planteamiento metodológico de la asignatura «Competencias TIC» de la Universitat Oberta de Catalunya, la cual se desarrolla a través de un proyecto colaborativo en red organizado en cuatro fases: inicio, estructuración, desarrollo y conclusión y cierre. Mediante una investigación evaluativa se triangulan datos de naturaleza cuantitativa y cualitativa provenientes de un cuestionario. Los resultados muestran la evolución en la propuesta metodológica de la asignatura a la vez que ponen de manifiesto cómo el proyecto digital en equipo facilita la adquisición de las competencias digitales, destacando concretamente las vinculadas al trabajo en equipo en red y la actitud digital. Las conclusiones refuerzan la importancia de los procesos CSCL, la necesidad de trabajar propuestas pedagógicas para la adquisición de competencias digitales. As a result of the emergence of Information and Communication Technologies (ICT) we are currently experiencing a period of major changes. Higher education plays a key role in helping students to acquire the competences which enable them to be autonomous in both academic and professional environments, where ICT literacy and collaborative processes are considered crucial. This study analyzes students’ perceptions about how the collaborative construction of an online project facilitates the acquisition of digital competences. It examines the methodological approach, within the context of the Open University of Catalonia, of the subject: «ICT Competences». This subject is conducted fully online at the UOC, and learners are required to engage in a collaborative project organized in 4 phases: starting, structuring, developing and concluding. Based on an evaluation research approach, quantitative and qualitative data from a survey have been triangulated. The results support the pedagogical methodology which forms the basis of this subject and indicates that collaborative projects facilitate the acquisition of digital competences, highlighting those linked to digital teamwork and digital attitude. The conclusions reinforce the importance of Computer Supported Collaborative Learning (CSCL) processes, the need to put forward pedagogical proposals for the acquisition of both digital and collaborative competences and the relevant role of the teacher in this process.

We introduce a computer vision problem from social cognition, namely, the automated detection of attitudes from a person's spontaneous facial expressions. To illustrate the challenges, we introduce two simple algorithms designed to predict observers' preferences between images (e.g., of celebrities) based on covert videos of the observers' faces. The two algorithms are almost as accurate as human judges performing the same task but nonetheless far from perfect. Our approach is to locate facial landmarks, then predict preference on the basis of their temporal dynamics. The database contains 768 videos involving four different kinds of preferences. We make it publically available.

Social interactions are a very important component in people's lives. Social network analysis has become a common technique used to model and quantify the properties of social interactions. In this paper, we propose an integrated framework to explore the characteristics of a social network extracted from multimodal dyadic interactions. For our study, we used a set of videos belonging to New York Times' Blogging Heads opinion blog. The Social Network is represented as an oriented graph, whose directed links are determined by the Influence Model. The links' weights are a measure of the "influence" a person has over the other. The states of the Influence Model encode automatically extracted audio/visual features from our videos using state-of-the art algorithms. Our results are reported in terms of accuracy of audio/visual data fusion for speaker segmentation and centrality measures used to characterize the extracted social network.

Background Health professionals and authorities strive to cope with heterogeneous data, services, and statistical models to support decision making on public health. Sophisticated analysis and distributed processing capabilities over geocoded epidemiological data are seen as driving factors to speed up control and decision making in these health risk situations. In this context, recent Web technologies and standards-based web services deployed on geospatial information infrastructures have rapidly become an efficient way to access, share, process, and visualize geocoded health-related information. Methods Data used on this study is based on Tuberculosis (TB) cases registered in Barcelona city during 2009. Residential addresses are geocoded and loaded into a spatial database that acts as a backend database. The web-based application architecture and geoprocessing web services are designed according to the Representational State Transfer (REST) principles. These web processing services produce spatial density maps against the backend database. Results The results are focused on the use of the proposed web-based application to the analysis of TB cases in Barcelona. The application produces spatial density maps to ease the monitoring and decision making process by health professionals. We also include a discussion of how spatial density maps may be useful for health practitioners in such contexts. Conclusions In this paper, we developed web-based client application and a set of geoprocessing web services to support specific health-spatial requirements. Spatial density maps of TB incidence were generated to help health professionals in analysis and decision-making tasks. The combined use of geographic information tools, map viewers, and geoprocessing services leads to interesting possibilities in handling health data in a spatial manner. In particular, the use of spatial density maps has been effective to identify the most affected areas and its spatial impact. This study is an attempt to demonstrate how web processing services together with web-based mapping capabilities suit the needs of health practitioners in epidemiological analysis scenarios.

Evaluating other individuals with respect to personality characteristics plays a crucial role in human relations and it is the focus of attention for research in diverse fields such as psychology and interactive computer systems. In psychology, face perception has been recognized as a key component of this evaluation system. Multiple studies suggest that observers use face information to infer personality characteristics. Interactive computer systems are trying to take advantage of these findings and apply them to increase the natural aspect of interaction and to improve the performance of interactive computer systems. Here, we experimentally test whether the automatic prediction of facial trait judgments (e.g. dominance) can be made by using the full appearance information of the face and whether a reduced representation of its structure is sufficient. We evaluate two separate approaches: a holistic representation model using the facial appearance information and a structural model constructed from the relations among facial salient points. State of the art machine learning methods are applied to a) derive a facial trait judgment model from training data and b) predict a facial trait value for any face. Furthermore, we address the issue of whether there are specific structural relations among facial points that predict perception of facial traits. Experimental results over a set of labeled data (9 different trait evaluations) and classification rules (4 rules) suggest that a) prediction of perception of facial traits is learnable by both holistic and structural approaches; b) the most reliable prediction of facial trait judgments is obtained by certain type of holistic descriptions of the face appearance; and c) for some traits such as attractiveness and extroversion, there are relationships between specific structural features and social perceptions.

A virtual laboratory is a virtual space where students are able to carry out practical activities. This paper presents an integrated structure for a virtual laboratory consisting on nine resources divided into pedagogical, human, and technological factors. Such a structure is based on the experience gained in design and development of virtual laboratories during the past 11 years in a virtual university. The proposed structure has been applied to different virtual laboratories, and this paper presents the special case of a virtual networking laboratory (VNLab) where students can access real networking devices. The VNLab structure described in this paper has been used at the Open University of Catalonia for the Cisco Networking Academic since 2001. Its suitability has been evaluated by the students using a Web questionnaire, and its correctness for the industrial electronics field has been analyzed.

In this paper we describe a proposal for standardizing the concept of competency in a repository of learning objects, by means of an extension of the LOM and the IMS-LD standards, and the use of ontologies for ensuring consistency is also outlined. Following the recommendations from the Bologna Process, we identify the competencies required and developed by means of the current learning resources and formative and evaluation activities in a virtual e-learning environment and, using the most important taxonomies defined for such purposes in the literature, we identify the necessary metadata to describe the competencies related to such learning resources and activities. We discuss the process of shifting from content based metadata to competency based metadata, and we present an example of improving the description of learning resources by adding metadata for describing competencies, using a real case at the Universitat Oberta de Catalunya.

In this work we investigate the importance of emotion awareness in e-learning environments, with emphasis to Computer Supported Collaborative Learning (CSCL) activities. Our presented solution involves a new conceptual model of emotions of interest in e-learning context. In the basis of this model, a computational model has been implemented employing self-report of emotions, affective feedback and effective emotion visualizations. Both models have been tested in real education settings, contributing to the research agenda.