https://uvadoc.uva.es/handle/10324/985 GSIC 2026-04-05T03:23:09Z https://uvadoc.uva.es/handle/10324/76150 Doctoral education (DE) suffers from widespread well-being issues. Recent evidence from short-term training actions shows potential to address them, but also large variability. Further, DE practitioners face challenges in understanding whether (and for whom) such interventions work, due to small sample sizes, short intervention durations, and the inherent uniqueness of each dissertation. This methodological paper proposes a novel, practice-oriented, and idiographic approach to such understanding, supported by learning analytics of quanti- tative and qualitative data. To illustrate this approach, we apply it to two datasets from six authentic doctoral workshops (N = 105 doctoral students), showcasing how it can provide individualized practice-oriented insights to doctoral students and help trainers better understand their interventions, while coping with typical limitations of data from doctoral training. These findings exemplify how the triangulation of simple, interpretable analytics models of mixed longitudinal data can improve students, practitioners’, and researchers’ understanding, re- design, and personalization of such training actions. Educational relevance and implications statement: Collecting data about the context and process of a doctoral training action can help practitioners and students understand who benefits more (or less) from such training. The individualized analysis of such data, obtained with even very simple technologies, can also help students understand their processes and contexts, to better address progress and well-being issues. The use of student- authored short narratives (e.g., diaries), along with longitudinal quantitative data, plays an important role in these personalized analyses, and the promise of automated qualitative coding makes this approach increasingly feasible 2025-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/59003 Background:Providing feedback in massive open online courses (MOOCs) is chal-lenging due to the massiveness and heterogeneity of learners' population. Learninganalytics (LA) solutions aim at scaling up feedback interventions and supportinginstructors in this endeavour.Paper Objectives:This paper focuses on instructor-led feedback mediated by LAtools in MOOCs. Our goal is to answer how, to what extent data-driven feedback isprovided to learners, and what its impact is.Methods:We conducted a systematic literature review on the state-of-the-art LA-informed instructor-led feedback in MOOCs. From a pool of 227 publications, weselected 38 articles that address the topic of LA-informed feedback in MOOCs medi-ated by instructors. We applied etic content analysis to the collected data.Results and Conclusions:The results revealed a lack of empirical studies exploring LA todeliver feedback, and limited attention on pedagogy to inform feedback practices. Our find-ings suggest the need for systematization and evaluation of feedback. Additionally, there isa need for conceptual tools to guide instructors' in the design of LA-based feedback.Takeaways:We point out the need for systematization and evaluation of feedback. Weenvision that this research can support the design of LA-based feedback, thus contribut-ing to bridge the gap between pedagogy and data-driven practice in MOOCs. 2023-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/53064 Smart Education requires bridging formal and informal learning experience. However, how to create contextualized learning resources that support this bridging remains a problem. In this paper, we propose to exploit the open data available in the Web to automatically create contextualized learning resources. Our preliminary results are promising, as our system creates thousands of learning resources related to formal education concepts and physical locations in the student’s local municipality. As part of our future work, we will explore how to integrate these resources into a Smart Learning Environment. 2019-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49295 LocalizARTE es una aplicación distribuida para publicar y realizar actividades educativas relacionadas con historia del arte donde la información que utiliza de partida ha sido generada a partir de datos abiertos ofrecidos por distintas organizaciones y las anotaciones que se realicen se proporcionarán también como datos abiertos. Su objetivo es apoyar al aprendizaje en diferentes espacios físicos y virtuales. En este artículo se ilustrará la ontología utilizada para las anotaciones y el funcionamiento, la arquitectura y cómo se está implementando la aplicación. Se describirá a través de un escenario de ejemplo donde un profesor de Historia del Arte publica nuevas tareas educativas en LocalizARTE con el objetivo de que sus estudiantes visiten y analicen los monumentos y edificios de su entorno. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49292 Smart Learning Environments are conceived as environments able to understand the student needs and context, and to propose adapted informal learning activities that might involve physical and virtual elements. However, SLEs can potentially fail in engaging students to perform such generated tasks as they are not part of the learning design and they might not be assessed by the teacher. Therefore, considering the positive effects observed in other educational environments, gamification is proposed to increase the student engagement and participation in such informal activities. Nevertheless, the gamification of activities that are not part of the learning design and which are generated on-the-fly becomes a difficult task as the gamification design needs to be created on the run without the intervention of the teacher. To make this process meaningful, the cornerstone is the adequate use of Learning Analytics and Learning Design information. This work-in-progress paper introduces a technological architecture supporting this type of gamification, and Smart GamiTool, a prototype of a smart learning environment supporting the orchestration and enactment of smart gamification. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49291 Smart Learning Environments and Learning Analytics hold promise of providing personalized support to learners according to their individual needs and context. This support can be achieved by collecting and analyzing data from the different learning tools and systems that are involved in the learning experience. This paper presents a first exploration of requirements and considerations for the integration of two systems: MBOX, a Multimodal Learning Analytics system for the physical space (human behavior and learning context), and SCARLETT, an SLE for the support during across-spaces learning situations combining different learning systems. This integration will enable the SLE to have access to a new and wide range of information, notably students’ behavior and social interactions in the physical learning context (e.g. classroom). The integration of multimodal data with the data coming from the digital learning environments will result in a more holistic system, therefore producing learning analytics that trigger personalized feedback and learning resources. Such integration and support is illustrated with a learning scenario that helps to discuss how these analytics can be derived and used for the intervention by the SLE. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49290 Supporting teachers to represent their teaching ideas has attracted researchers’ interest in developing digital learning design tools that provide some form of guidance around the design practice in a Technology-Enhanced Learning (TEL) environment. This paper reports on a study in a teacher education context utilising WebCollage as the learning design tool. The research focuses on teachers’ needs on determining resources and technologies while designing for TEL. Our findings convey that teachers’ needs converge towards a learning design tool providing flexibility to the designer to either (i) utilise a sound scaffolding mechanism incorporating a taxonomy that follows technology advancements or (ii) determine applying resources and technologies without providing any guidance. These findings may stimulate momentum for further attention to researchers involved with learning design tools’ development. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49287 Self-Regulated Learning (SRL) competence is imperative to academic achievement. For reflective academic writing tasks, which are common for university assessments, this is especially the case since students are often required to plan the task independently to be successful. The purpose of the current study was to examine different reflection behaviours of postgraduate students that were required to reflect on individual tasks over a fifteen-week-long higher education course. Forty students participated in a standardised questionnaire at the beginning of the course to assess their SRL competence and then participated in weekly individual reflection tasks on Google Docs. We examined students’ reflective writing behaviours based on time-series and correlation analysis of fine-grained data retrieved from Google Docs. More specifically, reflection behaviours between students with high SRL and low SRL competence were investigated. The results show that students with high SRL competence tend to reflect more frequently and more systematically than students with low SRL competence. Even though no statistically significant difference in academic performance between the two groups was found, there were statistical correlations between academic performance and individual reflective writing behaviours. We conclude the paper with a discussion on the insights into the temporal reflection patterns of different SRL competence student clusters, the impact of these behaviours on students’ academic performance, and potential suggestions for appropriate support for students with different levels of SRL. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49286 Educawood is a socio-semantic annotation system intended for environmental learning in Secondary and Higher Education. It can be used to socially annotate trees and other ecosystem structures such as dead wood. Furthermore, Educawood allows the exploration of existing semantic datasets of land cover maps and forestry inventories as well as social tree annotations (all released as Linked Open Data). Teachers can browse these data to propose contextualized environmental education activities, e.g. finding and annotating singular trees. Students can go on a field trip and use Educawood with their mobile devices to submit tree annotations. Follow-up activities can exploit socially-created tree annotations, for example in virtual field trips. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49248 The uptake of personalised approaches in education apart from students’ learning needs should also involve teachers’ needs. This paper addresses the understudied topic of integrating a Recommender System (RS) in a Learning Design (LD) environment as a means to personalise the support offered to teachers for designing learning. We present a study in a teacher education context, collecting teachers’ perceptions of learning design recommendations to explore the recommendation form and method that teachers value while designing. Our findings point out teachers’ appreciation of an LD environment integrating a macro form of recommending entire learning designs alike learning objects in online educational repositories. They also favour complementing the macro with a micro form that supports the LD process by recommending specific elements within a learning design. Our study indicates the need for a hybrid recommendation method appropriately filtering a learning design’s context and evaluation. Also, this research justifies the need to integrate an RS in an LD environment, reporting as teachers’ anticipated benefits (i) stimulating the initiation of designing for learning, (ii) advancing their LD practice by conceiving new design ideas, and (iii) providing a means of developing their LD experience effectively. The anticipated challenges point out the requirement of an RS that provides appropriate recommendations and the high need to cultivate teachers’ LD knowledge and mindset towards employing LD environments and RSs effectively. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49247 Designing for effective and efficient pedagogical interventions and orchestration in complex technology-enhanced learning (TEL) ecosystems is an increasingly challenging issue. Learning analytics (LA) solutions are very promising for purposes of understanding and optimizing learning and the environments in which it occurs. Moreover, LA solutions may contribute to an improved evidence-based Teacher Inquiry into Student Learning. However, it is still unclear how can LA be designed to position teachers as designers of effective interventions and orchestration actions. This chapter argues for human-centered design (HCD) and orchestration of actionable learning analytics, and it proposes three HCD principles for LA solutions, i.e., agentic positioning of teachers and other stakeholders, integration of the learning design cycle and the LA design process, and reliance on educational theories to guide the LA solution design and implementation. The HCD principles are illustrated and discussed through two case studies in authentic learning contexts. This chapter aims at contributing to move the research community in relation to the design and implementation of Human-Centered Learning Analytics solutions for complex technology-enhanced learning ecosystems. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49245 Detecting learners who face problems in MOOCs usually poses difficulties due to the high instructor-learners ratio, the diversity of the population, and the asynchronous participation mode. Existing solutions mainly draw on self-reported problems in discussion forums and on dashboards displaying learners’ activity traces. However, these approaches cannot scale up easily or do not consider the course learning design. This paper presents a conceptual framework aimed at guiding MOOC instructors in the identification of potential learners' problems and indicators of such problems, considering the learning design of the course (e.g., types of activities, difficulty, etc.). An instrumental qualitative case study served for the evaluation and refinement of the framework. The results showed that the framework positively helped instructors to reflect on potential learners’ problems they had not considered beforehand, and to associate such problems with a set of indicators related to their learning designs. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49219 This PhD research explores how Smart Learning Environments can support the connection between formal and informal learning. Thanks to the information offered by learning systems and tools such as Virtual Learning Environments, mobile and Internet of Things devices, SLEs can characterize the individual learning needs and context of students to provide them with personalized support across the boundaries of the classroom. In a similar fashion to approaches related with mobile learning, the connection offered by SLEs can help students to reflect on learning concepts in real scenarios, but also adapting the offered resources to their progression and performance throughout the learning situation. However, existing attempts in SLEs face difficulties regarding the preparation of possible interventions by teachers or the understanding of the formal learning situation. This work attempts to overcome this limitations with the usage of the learning design. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49218 This paper presents SLEek, an ontology for the context-aware recommendation of learning activities in Smart Learning Environments (SLEs). SLEek creates an actor-artifact network that is especially suitable for the context-aware recommendation of activities across spaces in formal and informal contexts. SLEek implementation reuses vocabularies from the Web of Data and is currently used in a dataset of 17K learning activities. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49211 Learners have ubiquitous informal learning opportunities, but it is difficult to take advantage from them and relate them to their formal education. The connection of formal and informal learning is one of the aims of SLEs, but how to do it is still a question. This paper explores such connection by integrating the mobile application Casual Learn to the SLE SCARLETT and it discusses the challenges faced in such integration. 2021-01-01T00:00:00Z https://uvadoc.uva.es/handle/10324/49208 Los entornos de aprendizaje inteligentes (SLE) proponen situaciones de aprendizaje a través de contextos formales e informales, utilizando para ello tecnologías diversas. Parte del problema es contar con un modelo de datos que permita compartir información entre dichas tecnologías y que tenga en cuenta las particularidades de los SLE. El presente artículo propone una ontología con esta finalidad. Para ello se parte de un ejemplo que ilustra el tipo de escenario que se da en los SLE, considerando aspectos como la integración de tecnología diversa, la personalización del proceso de aprendizaje y la conexión del aprendizaje en entornos formales e informales. A partir de estos aspectos -recogidos en la literatura y ejemplificados en el escenario- se extienden modelos de datos existentes para satisfacer las necesidades de los SLE. Esta extensión permite definir una red de actores y artefactos de aprendizaje enlazados por sus temas de interés, así como relacionar actividades de aprendizaje con entornos formales o informales. También se propone una implementación de este modelo en una ontología utilizando tecnologías de la Web Semántica para así favorecer la reutilización de datos ofrecidos por terceros. 2020-01-01T00:00:00Z