MSMarcos Da Silveira

Marcos Da Silveira

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Marcos Da Silveira has a total of 76 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Prioritising substances of concern for monitoring by using knowledge graphs and public datasets

    by Oona Freudenthal, Marcos Da Silveira, Louis Deladiennée, Ruth Moeller

    Air pollution is identified by the World Health Organisation (WHO) as the leading environmental threat to human health, with indoor exposure particularly concerning given its daily, long-term nature. Europeans spend approximately 90% of their time indoors, where poor indoor air quality (IAQ) contributes an estimated 2 million disability-adjusted life-years lost annually in the EU, with vulnerable populations especially at risk. This study explores a Knowledge Graph (KG) as a decision-support tool to prioritise Substances of Concern (SoC) for indoor dust and air. Two complementary approaches were applied: a top-down screening that filters a broad substance universe against defined criteria to identify monitoring candidates, and a bottom-up characterisation of already monitored substances against the same criteria. Integrating publicly available chemical data within the KG and applying a risk-oriented approach based on hazard classification, REACH registration tonnage and use information, we narrowed a list of over 16,000 substances (PlastChem list) down to 42. This work shows that KG can effectively connect diverse data sources and identified both known and emerging SoC not yet monitored in private settings. It highlights that non-REACH chemicals may contribute significantly to indoor dust chemistry analysis, and REACH consumer-use data alone does not capture all uses relevant to residential indoor exposure. The experiments show that expanding the number and diversity of integrated data sources is recommended to refine scoping for chemical monitoring, risk assessment and management. Key concerns among identified substances include reproductive toxicity and respiratory tract irritation, often linked to numerous consumer products. The ECHA Classification and Labelling Inventory was found to be a useful hazardous substance pool, though further refinement with additional health-related data is recommended. Finally, we discuss how integrating Large Language Models (LLMs) and KG into the framework could support partial automation of the validation of SoC, improving future monitoring and analysis efficiency.

  • Open Access

    Survey in characterizing semantic change

    by Jader Martins Camboim de Sá, Marcos Da Silveira, Cédric Pruski

    Living languages continuously evolve to reflect the cultural changes of human societies. This evolution manifests through neologisms (new words) or the semantic change of existing words (new meanings for existing words). Understanding the meaning of words is vital for interpreting texts from different cultures (regionalisms or slang), domains (e.g., technical terms), or time periods. In computer science, this phenomenon is relevant to computational linguistics tasks such as machine translation, information retrieval, and question answering. Semantic change can impact the performance of these applications, making it important to understand and characterize these changes formally. This problem has recently attracted significant attention from the computational linguistics community. Several approaches can detect semantic changes with good precision, but more effort is needed to characterize how word meanings change and to determine how to mitigate the impact of this phenomenon. This survey provides a comprehensive overview of existing approaches to the characterization of semantic change . We also formally define three classes of characterization: change in dimension (whether a word’s meaning becomes broader or narrower), change in orientation (whether a word acquires a more pejorative or ameliorative sense), and change in relation (whether a word is used in a new figurative context, such as a metaphor or metonymy). We demonstrate the applicability of this formalism on existing corpora, summarize the key aspects of selected publications, and discuss current needs and trends in research on semantic change characterization.

  • Open Access

    Deepening Citation Understanding in Scientific Literature via LLM-Powered Context Extraction

    by Thu Huong Nguyen, Cedric Pruski, Marcos Da Silveira

    Scientific progress relies on the complex, interconnected web of scholarly publications housed within digital libraries. While citations are the core mechanism for linking this knowledge, the simple reference alone fails to capture the intricate context in which the cited work is discussed. This lack of context poses a significant challenge for digital library algorithms seeking to understand scholarly influence. To address this, Citation Context Extraction (CCE) is a foundational task for transforming raw citations into meaningful, semantically rich links that can power advanced bibliometric analysis. This paper presents a novel, two-fold methodology for enhancing the CCE process. We first introduce an improved CCE method that leverages a richer set of textual features to more accurately identify citation context sentences, advancing beyond existing state-of-the-art techniques. Second, we propose an original approach that utilizes Large Language Models (LLMs) and advanced prompt engineering to perform a deeper, more nuanced and explainable semantic interpretation of the extracted contexts. We validate our methods on two distinct scientific corpora: ACL-ARC, a specialized dataset from computational linguistics and SDP-ACT, a more generic dataset spanning multiple disciplines. The results of our comparative analysis against state-of-the-art models demonstrate a significant improvement in CCE quality. Our contributions provide a crucial step toward building more intelligent and interpretable knowledge discovery systems, unlocking the full potential of digital libraries as platforms for understanding and mapping the intellectual lineage of scientific discourse.


  • Evaluating ESCO skill classifiers

    by Gabriele Marconi, Inès Baer, Marcos Da Silveira, Marie Gallais, Cédric Pruski

    ESCO skill classifiers, which scan job ads to identify skills at the finest level of the taxonomy, are widely used in international statistical projects and by national employment agencies. However, to our knowledge, no systematic evaluation of these classifiers has been conducted across large sets (i.e., thousands) of ESCO skills. We introduce a method for evaluating ESCO skill classifiers, addressing two key challenges: the large number of skills (up to around 14 000) and severe class imbalance. Our approach relies on matrix sampling of skills and job ads, with clustering and stratification, and uses bootstrapping to estimate standard errors for classifier comparisons. We apply the method to three classifiers using a sample of Luxembourgish IT and finance job ads. Our results indicate that the classifiers achieve acceptable accuracy despite low recall. Notably, the text matching classifier performs competitively, even against methods based on large language models.


  • Open Access

    “Crying like a Baby”: Survival Analysis and the Multimodal Memory of Holocaust Survivors

    by Gabor Mihaly Toth, Mohamed Laib, Alina Bothe, Marcus Ma, Shrikanth Narayanan, Cedric Pruski, Marcos da Silveira

    This paper presents a novel application of survival analysis to study gender differences in emotional responses during Holocaust survivor testimonies. By analyzing 982 oral history interviews (454 women, 528 men) from the USC Shoah Foundation, we examine the temporal patterns of crying and sobbing events using multimodal analysis techniques. Our findings reveal that women survivors cry earlier and more frequently than men during their testimonies, with statistically significant differences in waiting times and recurrence patterns. Furthermore, we identify gender-specific triggers: women are more likely to cry when discussing forced labor, while men show emotional responses when discussing captivity, mistreatment, and religious topics. This study demonstrates how survival analysis can provide meaningful insights into the temporality and gendered nature of traumatic memory transmission in oral history interviews.

  • Bridging Skill Gaps: Combining Generative and Symbolic AI for Personalized Lifelong Learning Pathways

    by Cédric Pruski, Célia da Costa Pereira, Marcos Da Silveira, Gabriele Marconi, Marie Gallais, Andrea Tettamanzi


  • Open Access

    FAIR evaluation of ten widely used chemical datasets: Lessons learned and recommendations

    by Marcos Da Silveira, Oona Freudenthal, Louis Deladiennee

    This document focuses on databases disseminating data on (hazardous) substances found on the North American and the European (EU) market. The goal is to analyse the FAIRness (Findability, Accessibility, Interoperability and Reusability) of published open data on these substances and to qualitatively evaluate to what extend the selected databases already fulfil the criteria set out in the commission draft regulation on a common data chemicals platform. We implemented two complementary approaches: Manual, and Automatic. The manual approach is based on online questionnaires. These questionnaires provide a structured approach to evaluating FAIRness by guiding users through a series of questions related to the FAIR principles. They are particularly useful for initiating discussions on FAIR implementation within research teams and for identifying areas that require further attention. Automated tools for FAIRness assessment, such as F-UJI and FAIR Checker, are gaining prominence and are continuously under development. Unlike manual tools, automated tools perform a series of tests automatically starting from a dereferenceable URL to the data resource to be evaluated. We analysed ten widely adopted datasets managed in Europe and North America. The highest score from automatic analysis was 54/100. The manual analysis shows that several FAIR metrics were satisfied, but not detectable by automatic tools because there is no metadata, or the format of the information was not a standard one. Thus, it was not interpretable by the tool. We present the details of the analysis and tables summarizing the outcomes, the issues, and the suggestions to address these issues.


  • A knowledge-sharing platform for space resources

    by Marcos Da Silveira, Louis Deladiennee, Emmanuel Scolan, Cedric Pruski


  • Open Access

    Analysis and implementation of the DynDiff tool when comparing versions of ontology

    by Sara Diaz Benavides, Silvio D. Cardoso, Marcos Da Silveira, Cédric Pruski

    Background: Ontologies play a key role in the management of medical knowledge because they have the properties to support a wide range of knowledge-intensive tasks. The dynamic nature of knowledge requires frequent changes to the ontologies to keep them up-to-date. The challenge is to understand and manage these changes and their impact on depending systems well in order to handle the growing volume of data annotated with ontologies and the limited documentation describing the changes. Methods: We present a method to detect and characterize the changes occurring between different versions of an ontology together with an ontology of changes entitled DynDiffOnto, designed according to Semantic Web best practices and FAIR principles. We further describe the implementation of the method and the evaluation of the tool with different ontologies from the biomedical domain (i.e. ICD9-CM, MeSH, NCIt, SNOMEDCT, GO, IOBC and CIDO), showing its performance in terms of time execution and capacity to classify ontological changes, compared with other state-of-the-art approaches. Results: The experiments show a top-level performance of DynDiff for large ontologies and a good performance for smaller ones, with respect to execution time and capability to identify complex changes. In this paper, we further highlight the impact of ontology matchers on the diff computation and the possibility to parameterize the matcher in DynDiff, enabling the possibility of benefits from state-of-the-art matchers. Conclusion: DynDiff is an efficient tool to compute differences between ontology versions and classify these differences according to DynDiffOnto concepts. This work also contributes to a better understanding of ontological changes through DynDiffOnto, which was designed to express the semantics of the changes between versions of an ontology and can be used to document the evolution of an ontology.