Abstract
Transformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (llms). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose llms using simple prompts; (ii) effectiveness of different emotion prompt designs with llms; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70% with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that llms require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.

Abstract
A unique dataset of marine atmospheric electric field observations over the Atlantic Ocean is described. The data are relevant not only for atmospheric electricity studies, but more generally for studies of the Earth's atmosphere and climate variability, as well as space-Earth interaction studies. In addition to the atmospheric electric field data, the dataset includes simultaneous measurements of other atmospheric variables, including gamma radiation, visibility, and solar radiation. These ancillary observations not only support interpretation and understanding of the atmospheric electric field data, but also are of interest in themselves. The entire framework from data collection to final derived datasets has been duly documented to ensure traceability and reproducibility of the whole data curation chain. All the data, from raw measurements to final datasets, are preserved in data repositories with a corresponding assigned DOI. Final datasets are available from the Figshare repository (https://figshare.com/projects/SAIL_Data/178500, ), and computational notebooks containing the code used at every step of the data curation chain are available from the Zenodo repository (https://zenodo.org/communities/sail, Project SAIL community, 2025).

Abstract
This viewpoint highlights the critical need for proactive and strategic integration of digital health tools into heat-health action plans (HHAPs) across Europe. Drawing insights from the digital health surge during the COVID-19 pandemic and recent heat-related health impacts, we identify response gaps and suggest specific strategies to strengthen current plans. Key recommendations include leveraging mobile health communication, expanding telemedicine usage, adopting wearable health monitoring devices, and using advanced data analytics to improve responsiveness and equity. This perspective aims to guide policymakers, health authorities, and health care providers in systematically enhancing heat-health preparedness through digital health innovation.

Abstract
Providing healthcare professionals with quick access to structured standardized information enables comprehensive analysis and improves clinical decision-making. However, an important part of the records in health institutions is in the form of free text. This paper proposes a pipeline that automatically extracts medical information from Electronic Medical Records (EMRs), based on large language models (LLMs) and a domain ontology defined and validated in collaboration with a medical expert. The output is a knowledge graph of clinical narratives that can be used to search through repositories of EMRs or discover new facts. To promote the standardization of the extracted medical terms, we link them to existing international coding systems using biomedical repositories (UMLS - Unified Medical Language System and BioPortal - Biomedical Ontology Repository). We showcase our approach on a set of Portuguese clinical texts of cases of Acute Myeloid Leukemia (AML) guided by one medical expert. We evaluate the quality of the extraction and of the knowledge graph. © 2025 Elsevier B.V., All rights reserved.

Abstract
[No abstract available]

Abstract
Subgroup discovery aims to identify interpretable segments of a dataset where model behavior deviates from global trends. Traditionally, this involves uncovering patterns among data instances with respect to a target property, such as class labels or performance metrics. For example, classification accuracy can highlight subpopulations where models perform unusually well or poorly. While effective for model auditing and failure analysis, accuracy alone provides a limited view, as it does not reflect model confidence or sources of uncertainty. This work proposes a complementary approach: subgroup discovery using model uncertainty. Rather than identifying where the model fails, we focus on where it is systematically uncertain, even when predictions are correct. Such uncertainty may arise from intrinsic data ambiguity (aleatoric) or poor data representation in training (epistemic). It can highlight areas of the input space where the model’s predictions are less robust or reliable. We evaluate the feasibility of this approach through controlled experiments on the classification of synthetic data and the Iris dataset. While our findings are exploratory and qualitative, they suggest that uncertainty-based subgroup discovery may uncover interpretable regions of interest, providing a promising direction for model auditing and analysis. © 2025 Elsevier B.V., All rights reserved.