Searcharxiv⌕ Search

arXiv subjects

Daniel Schwabe

Publications and source records attributed to Daniel Schwabe.

16 recordsLinked to original sources
arXiv2026

Metric Hub: A metric library and practical selection workflow for use-case-driven data quality assessment in medical AI

Machine learning (ML) in medicine has transitioned from research to concrete applications aimed at supporting several medical purposes like therapy selection, monitoring and treatment. Acceptance and effective adoption by clinicians and patients, as well as regulatory approval, require evidence of trustworthiness. A major factor for the development of trustworthy AI is the quantification of data quality for AI model training and testing. We have recently proposed the METRIC-framework for systematically evaluating the suitability (fit-for-purpose) of data for medical ML for a given task. Here, we operationalize this theoretical framework by introducing a collection of data quality metrics - the metric library - for practically measuring data quality dimensions. For each metric, we provide a metric card with the most important information, including definition, applicability, examples, pitfalls and recommendations, to support the understanding and implementation of these metrics. Furthermore, we discuss strategies and provide decision trees for choosing an appropriate set of data quality metrics from the metric library given specific use cases. We demonstrate the impact of our approach exemplarily on the PTB-XL ECG-dataset. This is a first step to enable fit-for-purpose evaluation of training and test data in practice as the base for establishing trustworthy AI in medicine.

cs.LG↗
arXiv2025

The MEVIR 2 Framework: A Virtue-Informed Moral-Epistemic Model of Human Trust Decisions

The MEVIR 2 framework innovates and improves how we understand trust decisions in our polarized information landscape. Unlike classical models assuming ideal rationality, MEVIR 2 recognizes that human trust emerges from three interacting foundations: how we process evidence procedurally, our character as epistemic agents virtue theory, and our moral intuitions shaped by both evolutionary cooperation MAC model and cultural values Extended Moral Foundations Theory. This explains why different people find different authorities, facts, and tradeoffs compelling. MEVIR 2's key innovation introduces "Truth Tribes" TTs-stable communities sharing aligned procedural, virtue, and moral epistemic profiles. These arent mere ideological groups but emergent clusters with internally coherent "trust lattices" that remain mutually unintelligible across tribal boundaries. The framework incorporates distinctions between Truth Bearers and Truth Makers, showing disagreements often stem from fundamentally different views about what aspects of reality can make propositions true. Case studies on vaccination mandates and climate policy demonstrate how different moral configurations lead people to select different authorities, evidential standards, and trust anchors-constructing separate moral epistemic worlds. The framework reinterprets cognitive biases as failures of epistemic virtue and provides foundations for designing decision support systems that could enhance metacognition, make trust processes transparent, and foster more conscientious reasoning across divided communities. MEVIR 2 thus offers both descriptive power for understanding polarization and normative guidance for bridging epistemic divides.

cs.CY↗
arXiv2025

The MEVIR Framework: A Virtue-Informed Moral-Epistemic Model of Human Trust Decisions

The 21st-century information landscape presents an unprecedented challenge: how do individuals make sound trust decisions amid complexity, polarization, and misinformation? Traditional rational-agent models fail to capture human trust formation, which involves a complex synthesis of reason, character, and pre-rational intuition. This report introduces the Moral-Epistemic VIRtue informed (MEVIR) framework, a comprehensive descriptive model integrating three theoretical perspectives: (1) a procedural model describing evidence-gathering and reasoning chains; (2) Linda Zagzebski's virtue epistemology, characterizing intellectual disposition and character-driven processes; and (3) Extended Moral Foundations Theory (EMFT), explaining rapid, automatic moral intuitions that anchor reasoning. Central to the framework are ontological concepts - Truth Bearers, Truth Makers, and Ontological Unpacking-revealing that disagreements often stem from fundamental differences in what counts as admissible reality. MEVIR reframes cognitive biases as systematic failures in applying epistemic virtues and demonstrates how different moral foundations lead agents to construct separate, internally coherent "trust lattices". Through case studies on vaccination mandates and climate policy, the framework shows that political polarization represents deeper divergence in moral priors, epistemic authorities, and evaluative heuristics. The report analyzes how propaganda, psychological operations, and echo chambers exploit the MEVIR process. The framework provides foundation for a Decision Support System to augment metacognition, helping individuals identify biases and practice epistemic virtues. The report concludes by acknowledging limitations and proposing longitudinal studies for future research.

cs.CY↗
arXiv2024

The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review

The adoption of machine learning (ML) and, more specifically, deep learning (DL) applications into all major areas of our lives is underway. The development of trustworthy AI is especially important in medicine due to the large implications for patients' lives. While trustworthiness concerns various aspects including ethical, technical and privacy requirements, we focus on the importance of data quality (training/test) in DL. Since data quality dictates the behaviour of ML products, evaluating data quality will play a key part in the regulatory approval of medical AI products. We perform a systematic review following PRISMA guidelines using the databases PubMed and ACM Digital Library. We identify 2362 studies, out of which 62 records fulfil our eligibility criteria. From this literature, we synthesise the existing knowledge on data quality frameworks and combine it with the perspective of ML applications in medicine. As a result, we propose the METRIC-framework, a specialised data quality framework for medical training data comprising 15 awareness dimensions, along which developers of medical ML applications should investigate a dataset. This knowledge helps to reduce biases as a major source of unfairness, increase robustness, facilitate interpretability and thus lays the foundation for trustworthy AI in medicine. Incorporating such systematic assessment of medical datasets into regulatory approval processes has the potential to accelerate the approval of ML products and builds the basis for new standards.

cs.LG↗
arXiv2022

A Functional Model For Information Exploration Systems

Information exploration tasks are inherently complex, ill-structured, and involve sequences of actions usually spread over many sessions. When exploring a dataset, users tend to experiment higher degrees of uncertainty, mostly raised by knowledge gaps concerning the information sources, the task, and the efficiency of the chosen exploration actions, strategies, and tools in supporting the task solution process. Provided these concerns, exploration tools should be designed with the goal of leveraging the mapping between user's cognitive actions and solution strategies onto the current systems' operations. However, state-of-the-art systems fail in providing an expressive set of operations that covers a wide range of exploration problems. There is not a common understanding of neither which operators are required nor in which ways they can be used by explorers. In order to mitigate these shortcomings, this work presents a formal framework of exploration operations expressive enough to describe at least the majority of state-of-the-art exploration interfaces and tasks. We also show how the framework leveraged a new evaluation approach, where we draw precise comparisons between tools concerning the range of exploration tasks they support.

cs.HC↗
arXiv2021

A Study of the Quality of Wikidata

Wikidata has been increasingly adopted by many communities for a wide variety of applications, which demand high-quality knowledge to deliver successful results. In this paper, we develop a framework to detect and analyze low-quality statements in Wikidata by shedding light on the current practices exercised by the community. We explore three indicators of data quality in Wikidata, based on: 1) community consensus on the currently recorded knowledge, assuming that statements that have been removed and not added back are implicitly agreed to be of low quality; 2) statements that have been deprecated; and 3) constraint violations in the data. We combine these indicators to detect low-quality statements, revealing challenges with duplicate entities, missing triples, violated type rules, and taxonomic distinctions. Our findings complement ongoing efforts by the Wikidata community to improve data quality, aiming to make it easier for users and editors to find and correct mistakes.

cs.AI↗
arXiv2021

Information Disorders, Moral Values and the Dispute of Narratives

In this paper we propose a framework characterizing information disorders as disputes of narratives. Such narratives present claims to readers, who must decide whether to accept the statements in the claims as facts. We point out that this process requires establishing connections to moral values, since it has been shown that human decision making is heavily dependent on them. A simple example illustrating how this could be done is given, related to claims about fraud in the US 2020 Presidential elections.

cs.CY↗
arXiv2021

KGTK: A Toolkit for Large Knowledge Graph Manipulation and Analysis

Knowledge graphs (KGs) have become the preferred technology for representing, sharing and adding knowledge to modern AI applications. While KGs have become a mainstream technology, the RDF/SPARQL-centric toolset for operating with them at scale is heterogeneous, difficult to integrate and only covers a subset of the operations that are commonly needed in data science applications. In this paper we present KGTK, a data science-centric toolkit designed to represent, create, transform, enhance and analyze KGs. KGTK represents graphs in tables and leverages popular libraries developed for data science applications, enabling a wide audience of developers to easily construct knowledge graph pipelines for their applications. We illustrate the framework with real-world scenarios where we have used KGTK to integrate and manipulate large KGs, such as Wikidata, DBpedia and ConceptNet.

cs.AI↗
arXiv2020

A Cluster-Matching-Based Method for Video Face Recognition

Face recognition systems are present in many modern solutions and thousands of applications in our daily lives. However, current solutions are not easily scalable, especially when it comes to the addition of new targeted people. We propose a cluster-matching-based approach for face recognition in video. In our approach, we use unsupervised learning to cluster the faces present in both the dataset and targeted videos selected for face recognition. Moreover, we design a cluster matching heuristic to associate clusters in both sets that is also capable of identifying when a face belongs to a non-registered person. Our method has achieved a recall of 99.435% and a precision of 99.131% in the task of video face recognition. Besides performing face recognition, it can also be used to determine the video segments where each person is present.

cs.CV↗
arXiv2020

Commonsense Knowledge in Wikidata

Wikidata and Wikipedia have been proven useful for reason-ing in natural language applications, like question answering or entitylinking. Yet, no existing work has studied the potential of Wikidata for commonsense reasoning. This paper investigates whether Wikidata con-tains commonsense knowledge which is complementary to existing commonsense sources. Starting from a definition of common sense, we devise three guiding principles, and apply them to generate a commonsense subgraph of Wikidata (Wikidata-CS). Within our approach, we map the relations of Wikidata to ConceptNet, which we also leverage to integrate Wikidata-CS into an existing consolidated commonsense graph. Our experiments reveal that: 1) albeit Wikidata-CS represents a small portion of Wikidata, it is an indicator that Wikidata contains relevant commonsense knowledge, which can be mapped to 15 ConceptNet relations; 2) the overlap between Wikidata-CS and other commonsense sources is low, motivating the value of knowledge integration; 3) Wikidata-CS has been evolving over time at a slightly slower rate compared to the overall Wikidata, indicating a possible lack of focus on commonsense knowledge. Based on these findings, we propose three recommended actions to improve the coverage and quality of Wikidata-CS further.

cs.AI↗
arXiv2019

Trust and Privacy in Knowledge Graphs

This paper presents the KG Usage framework, which allows the introduction of KG features to support Trust, Privacy and Transparency concerns regarding the use of its contents by applications. A real-world example is presented and used to illustrate how the framework can be used.

cs.CY↗
arXiv2018

A Framework to Support the Trust Process in News and Social Media

Current society is heavily influenced by the spread of online information, containing all sorts of claims, commonly found in news stories, tweets, and social media postings. Depending on the user, they may be considered "true" or "false", according to the agent's trust on the claim. In this paper, we discuss the concept of content trust and trust process, and propose a framework to describe the trust process, which can support various possible models of content trust.

cs.SI↗
arXiv2018

Ontologies for Representing Relations among Political Agents

The Internet and the Web are now an integral part of the way most modern societies, and corresponding political systems, work. We regard Political systems as the formal and informal political processes by which decisions are made concerning the use, production and distribution of resources in any given society. Our focus in on the sets of agents - Persons and Organizations - that govern a society, and their relations. We present a set of ontologies aimed at characterizing different kinds of direct and indirect relations that occur within a Political System. The goal is to provide a more semantically precise basis for determining more abstract notions such as "influence". These ontologies are being used for the "Se Liga na Politica" project, whose goal is to provide an open linked data database of Political Agents in Brazil. Whereas they are being used in a particular political system, these ontologies can be applied to different political systems.

cs.CY↗
arXiv2011

SERIMI - Resource Description Similarity, RDF Instance Matching and Interlinking

The interlinking of datasets published in the Linked Data Cloud is a challenging problem and a key factor for the success of the Semantic Web. Manual rule-based methods are the most effective solution for the problem, but they require skilled human data publishers going through a laborious, error prone and time-consuming process for manually describing rules mapping instances between two datasets. Thus, an automatic approach for solving this problem is more than welcome. In this paper, we propose a novel interlinking method, SERIMI, for solving this problem automatically. SERIMI matches instances between a source and a target datasets, without prior knowledge of the data, domain or schema of these datasets. Experiments conducted with benchmark collections demonstrate that our approach considerably outperforms state-of-the-art automatic approaches for solving the interlinking problem on the Linked Data Cloud.

cs.DB↗
arXiv2003

Web Engineering

Web Engineering is the application of systematic, disciplined and quantifiable approaches to development, operation, and maintenance of Web-based applications. It is both a pro-active approach and a growing collection of theoretical and empirical research in Web application development. This paper gives an overview of Web Engineering by addressing the questions: a) why is it needed? b) what is its domain of operation? c) how does it help and what should it do to improve Web application development? and d) how should it be incorporated in education and training? The paper discusses the significant differences that exist between Web applications and conventional software, the taxonomy of Web applications, the progress made so far and the research issues and experience of creating a specialisation at the master's level. The paper reaches a conclusion that Web Engineering at this stage is a moving target since Web technologies are constantly evolving, making new types of applications possible, which in turn may require innovations in how they are built, deployed and maintained.

cs.SE↗