In the context of Social Media literacy, the success of educational interventions relies on designing motivational learning environments that seek students’ engagement. Despite existing achievements in social media education to include more appealing resources (e.g. gamification, authentic learning, interactive simulations), limited research has explored the factors that influence students’ engagement. This study aims to investigate the factors that influence engagement in an educational social media platform. Specifically, the factors that shape interest and enjoyment in Instareal, an educational tool that combines narrative scripts and collaborative learning flow patterns to educate teenagers about social media risks and challenges. To answer our research questions, we analyze the log data generated by high school students (N = 100) who tested a Social Media Literacy training with the support of Instareal. A factor analysis and a backward stepwise regression is performed over a dataset containing students’ traces of online activities and social interactions. The results show that factors such as the social participation of the students (comments, likes), curiosity (opening profiles, following others), and the quality of their answers influence interest and enjoyment within the platform. The results of this study offer new insights into measuring and enhancing student engagement when using educational social media environments.

Predicting whether a newly submitted bug will be resolved quickly or slowly is a crucial aspect of the bug triage process, as it enables project managers to estimate software maintenance efforts and manage development workflows more effectively. This paper proposes a deep learning approach for classifying bug reports into two categories— FAST or SLOW —based on their expected fixing time. The method leverages a feature set composed of the bug description and reporter comments and adopts a transfer learning strategy using pre-trained Large Language Models (LLMs). The problem is framed as a supervised text classification task, where LLMs exploit their ability to learn rich contextual representations of language. We introduce a novel classification workflow that guides the LLM through a structured prompt, combining two design patterns: the persona pattern to contextualize the task and the input semantic pattern to organize textual information. The workflow relies on zero-shot learning to assess whether the intrinsic knowledge embedded in the LLMs is sufficient for this prediction task. We conducted a comprehensive evaluation of three state-of-the-art LLMs across multiple real-world datasets sourced from Bugzilla, encompassing a diverse range of software projects. The experimental results demonstrate that the proposed method is effective in accurately identifying fast-resolving bugs. Among the evaluated models, LLaMA3-8B consistently delivered superior performance. Additionally, the absence of statistically significant performance variations across datasets highlights the generalizability of the approach. Notably, the LLMs maintained strong performance even on small and imbalanced datasets, underscoring their robustness and practical applicability in real-world, data-scarce scenarios.

Abstract The spread of Augmented Reality (AR) and the recent technological developments, provide innovative techniques and tools that show a growing potential in education. One of the pilots of the European Horizon 2020 project ARETE (Augmented Reality Interactive Educational System) aims to investigate and evaluate for the first time the introduction of an AR solution to support a behavioral lesson in schools where the Positive Behaviour Intervention and Support (PBIS) methodology is adopted. Specifically in this paper, we describe the architectural design and implementation of a PBIS-AR application as a component of the ARETE ecosystem. It describes the functionality of the system and the teaching process that the AR solution will support.

The spread of new technologies like Augmented Reality and recent technological developments, provide innovative techniques and tools that show increasing potential in education. In this paper we will showcase the work implemented within the Horizon 2020 European project ARETE (Augmented Reality Interactive Educational System). One of the pilots of this project aims to investigate for the first time the introduction of AR to support a behavioral lesson in schools where Positive Behaviour Intervention and Support (PBIS) methodology is adopted. In particular, we present the study conducted to track user interactions with augmented reality objects through the use of the Experience API standard.

Concept maps are significant tools able to support several tasks in the educational area such as curriculum design, knowledge organization and modeling, students’ assessment and many others. They are also successfully used in learning activities in which students have to represent domain knowledge according to teacher’s assignment. In this context, the development of Learning Analytics approaches would benefit of methods that automatically compare concept maps. Detecting concept maps similarities is relevant to identify how the same concepts are used in different knowledge representations. Algorithms for comparing graphs have been extensively studied in the literature, but they do not appear appropriate for concept maps. In concept maps, concepts exposed are at least as relevant as the structure that contains them. Neglecting the semantic and didactic aspect inevitably causes inaccuracies and the consequently limited applicability in Learning Analytics approaches. In this work, starting from an algorithm which compares didactic characteristic of concept maps, we present an extension which exploits a semantic approach to catch the actual meaning of the concepts expressed in the nodes of the map.

A patient, nowadays, acquires health information from the Web mainly through a “human-to-machine”\ncommunication process with a generic search engine. This, in turn, affects, positively or negatively, his/her\nempowerment level and the “human-to-human” communication process that occurs between a patient and a\nhealthcare professional such as a doctor. A generic communication process can be modelled by considering\nits syntactic-technical, semantic-meaning, and pragmatic-effectiveness levels and an efficacious\ncommunication occurs when all the communication levels are fully addressed. In the case of retrieval of health\ninformation from the Web, although a generic search engine is able to work at the syntactic-technical level,\nthe semantic and pragmatic aspects are left to the user and this can be challenging, especially for elderly\npeople. This work presents a custom search engine, FACILE, that works at the three communication levels\nand allows to overcome the challenges confronted during the search process. A patient can specify his/her\ninformation requirements in a simple way and FACILE will retrieve the “right” amount of Web content in a\nlanguage that he/she can easily understand. This facilitates the comprehension of the found information and\npositively affects the empowerment process and communication with healthcare professionals.

The number of people looking for health information on the Internet is constantly growing. When searching for health information, different types of users, such as patients, clinicians or medical researchers, have different needs and should easily find the information they are looking for based on their specific requirements. However, generic search engines do not make any distinction among the users and, often, overload them with the provided amount of information. On the other hand, specific search engines mostly work on medical literature and specialized web sites are often not free and contain focused information built by hand. This paper presents a method to facilitate the search of health information on the web so that users can easily and quickly find information based on their specific requirements. In particular, it allows different types of users to find health web pages with required language complexity levels. To this end, we first use the structured data contained in the web to classify health web pages based on different audience types such as, patients, clinicians and medical researchers. Next, we evaluate the language complexity levels of the different web pages. Finally, we propose a mapping between the language complexity levels and the different audience types that allows us to provide different types of users, e.g., experts and non-experts with tailored web pages in terms of language complexity

Health Information Technology Systems (HITS) are increasingly used to improve the quality of patient care while reducing costs. These systems have been developed in response to the changing models of care to an ongoing relationship between patient and care team, supported by the use of technology due to the increased instance of chronic disease. However, the use of HITS may increase the risk to patient safety and security. While standards can be used to address and manage these risks, significant communication problems exist between experts working in different departments. These departments operate in silos often leading to communication breakdowns. For example, risk management stakeholders who are not clinicians may struggle to understand, define and manage risks associated with these systems when talking to medical professionals as they do not understand medical terminology or the associated care processes. In order to overcome this communication problem, we propose the use of the “Three Amigos” approach together with the use of the SIMPLE tool that has been developed to assist patients in understanding medical terms. This paper examines how the “Three Amigos” approach and the SIMPLE tool can be used to improve estimation of severity of risk by non-clinical risk management stakeholders and provides a practical example of their use in a ten step risk management process.

An important activity in the life of interpreters is terminology work.A primary method for learning technical vocabulary is the creation of personal glossaries.The current paper describes the design and creation of a system that guides the students in autonomous vocabulary work, supports the students' learning progress, and helps the teacher in monitoring the student commitment to and achievements in the creation of personal glossaries.The system includes a tool for the creation of glossaries, a tracking system that records the students' actions and the websites they visit while searching the Web for linguistic and content information, and a learning analytics dashboard.The system was tested on a class of 34 university students training in interpreting and the paper reports some preliminary results.

The public availability of datasets of teaching resources is an issue for the design, development and evaluation of Information Retrieval and Recommender Systems in Technology Enhanced Learning. Recently, the Dataset of Joint Educational Entities (DAJEE) has provided the community with a very exhaustive collection of resources coming from Massive Open Online Courses. This work proposes a representation of the DAJEE dataset according to Linked Data principles, interlinking the large amount of resources in DAJEE with the Web of Data. The transcript of the educational resources in DAJEE have been annotated through a Named Entity Recognition tool in order to create interlinks with the DBpedia entities. The DBpedia knowledge base provides additional information related to categories, that can be exploited to infer new knowledge and support reasoning processes.

In this paper, we present SaR-Web, a multimodal web search tool that provides automatic support to searching as learning processes. Inspired by the work of Richard Rogers and the Digital Methods Initiative, SaR-Web compares the results of queries across search engine language domains, and visualizes search results with a semantic added value, thus facilitating cross-linguistic and cross-cultural comparisons of results. The comparison between search results in different languages is enabled through the visualization of semantic concepts extracted by means of a NER tool from the search results. The SaR-Web system has the potential to support highlevel learning activities described in Bloom's taxonomy such as: identifying and analyzing patterns, comparing, integrating, and creating new ideas.

The LAK Data Challenge 2015 continues the research efforts of the previous data competitions in 2013 and 2014 by stimulating research on the evolving fields Learning Analytics (LA) and Educational Data Mining (EDM). Building on a series of activities of the LinkedUp project, the challenge aims to generate new insights and analysis on the LA & EDM disciplines and is supported through the LAK Dataset - a unique corpus of LA & EDM literature, exposed in structured and machine-readable formats.

The LAK Data Challenge 2014 continues the research efforts of the second edition by stimulating research on the evolving fields Learning Analytics (LA) and Educational Data Mining (EDM). Building on a series of activities of the LinkedUp project, the challenge aims to generate new insights and analysis on the LA & EDM disciplines and is supported through the LAK Dataset - a unique corpus of LA & EDM literature, exposed in structured and machine-readable formats.