Search

We describe FastCat Catalogues, a Web application that supports researchers studying archival material, such as historians, in exploring and quantitatively analysing the data (transcripts) of archival documents. The application was designed based on real information needs provided by a large group of researchers, makes use of JSON technology, and is configurable for use over any type of archival documents whose contents have been transcribed and exported in JSON format. The supported functionalities include a) source- or record-specific entity browsing, b) source-independent entity browsing, c) data filtering, d) inspection of provenance information, e) data aggregation and visualisation in charts, f) table and chart data export for further (external) analysis. The application is provided as open source and is currently used by historians in maritime history research., Comment: This is a preprint of a paper accepted for publication at the 2023 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

Archival research is a complicated task that involves several diverse activities for the extraction of evidence and knowledge from a set of archival documents. The involved activities are usually unconnected, in terms of data connection and flow, making difficult their recursive revision and execution, as well as the inspection of provenance information at data element level. This paper proposes a workflow model for holistic data management in archival research; from transcribing and documenting a set of archival documents, to curating the transcribed data, integrating it to a rich semantic network (knowledge graph), and then exploring the integrated data quantitatively. The workflow is provenance-aware, highly-recursive and focuses on semantic interoperability, aiming at the production of sustainable data of high value and long-term validity. We provide implementation details for each step of the workflow and present its application in maritime history research. We also discuss relevant quality aspects and lessons learned from its application in a real context., Comment: This is a preprint of an article accepted for publication in Digital Scholarship in the Humanities (DSH), published by Oxford University Press

We describe the construction and use of the SeaLiT Ontology, an extension of the ISO standard CIDOC-CRM for the modelling and integration of maritime history information. The ontology has been developed gradually, following a bottom-up approach that required the analysis of large amounts of real primary data (archival material) as well as knowledge and validation by domain experts (maritime historians). We present the specification of the ontology, RDFS and OWL implementations, as well as knowledge graphs that make use of this data model for integrating information originating from a large and diverse set of archival documents, such as crew lists, sailors registers, naval ship registers and payrolls. We also describe an application that operates over these knowledge graphs and which supports historians in exploring and quantitatively analysing the integrated data through a user-friendly interface. Finally, we discuss aspects related to the use, evolution and sustainability of the ontology., Comment: This is a preprint of an article accepted for publication at the ACM Journal on Computing and Cultural Heritage (JOCCH)

An increasing number of organisations in almost all fields have started adopting semantic web technologies for publishing their data as open, linked and interoperable (RDF) datasets, queryable through the SPARQL language and protocol. Link traversal has emerged as a SPARQL query processing method that exploits the Linked Data principles and the dynamic nature of the Web to dynamically discover data relevant for answering a query by resolving online resources (URIs) during query evaluation. However, the execution time of link traversal queries can become prohibitively high for certain query types due to the high number of resources that need to be accessed during query execution. In this paper we propose and evaluate baseline methods for estimating the evaluation cost of link traversal queries. Such methods can be very useful for deciding on-the-fly the query execution strategy to follow for a given query, thereby reducing the load of a SPARQL endpoint and increasing the overall reliability of the query service. To evaluate the performance of the proposed methods, we have created (and make publicly available) a ground truth dataset consisting of 2,425 queries.

A vast area of research in historical science concerns the documentation and study of artefacts and related evidence. Current practice mostly uses spreadsheets or simple relational databases to organise the information as rows with multiple columns of related attributes. This form offers itself for data analysis and scholarly interpretation, however it also poses problems including i) the difficulty for collaborative but controlled documentation by a large number of users, ii) the lack of representation of the details from which the documented relations are inferred, iii) the difficulty to extend the underlying data structures as well as to combine and integrate data from multiple and diverse information sources, and iv) the limitation to reuse the data beyond the context of a particular research activity. To support historians to cope with these problems, in this paper we describe the Synthesis documentation system and its use by a large number of historians in the context of an ongoing research project in the field of History of Art. The system is Web-based and collaborative, and makes use of existing standards for information documentation and publication (CIDOC-CRM, RDF), focusing on semantic interoperability and the production of data of high value and long-term validity., Comment: This is a preprint of an article accepted for publication at the 20th International Semantic Web Conference (ISWC 2021)

Descriptive and empirical sciences, such as History, are the sciences that collect, observe and describe phenomena in order to explain them and draw interpretative conclusions about influences, driving forces and impacts under given circumstances. Spreadsheet software and relational database management systems are still the dominant tools for quantitative analysis and overall data management in these these sciences, allowing researchers to directly analyse the gathered data and perform scholarly interpretation. However, this current practice has a set of limitations, including the high dependency of the collected data on the initial research hypothesis, usually useless for other research, the lack of representation of the details from which the registered relations are inferred, and the difficulty to revisit the original data sources for verification, corrections or improvements. To cope with these problems, in this paper we present FAST CAT, a collaborative system for assistive data entry and curation in Digital Humanities and similar forms of empirical research. We describe the related challenges, the overall methodology we follow for supporting semantic interoperability, and discuss the use of FAST CAT in the context of a European (ERC) project of Maritime History, called SeaLiT, which examines economic, social and demographic impacts of the introduction of steamboats in the Mediterranean area between the 1850s and the 1920s., Comment: This is a preprint of an article accepted for publication at the ACM Journal on Computing and Cultural Heritage (JOCCH)

Entity linking (EL) is the task of automatically identifying entity mentions in text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. Throughout the past decade, a plethora of EL systems and pipelines have become available, where performance of individual systems varies heavily across corpora, languages or domains. Linking performance varies even between different mentions in the same text corpus, where, for instance, some EL approaches are better able to deal with short surface forms while others may perform better when more context information is available. To this end, we argue that performance may be optimised by exploiting results from distinct EL systems on the same corpus, thereby leveraging their individual strengths on a per-mention basis. In this paper, we introduce a supervised approach which exploits the output of multiple ready-made EL systems by predicting the correct link on a per-mention basis. Experimental results obtained on existing ground truth datasets and exploiting three state-of-the-art EL systems show the effectiveness of our approach and its capacity to significantly outperform the individual EL systems as well as a set of baseline methods., Comment: SAC '20: Proceedings of the 35th Annual ACM Symposium on Applied Computing

Artificial Intelligence (AI)-based systems are widely employed nowadays to make decisions that have far-reaching impact on individuals and society. Their decisions might affect everyone, everywhere, and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training, and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multidisciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well-grounded in a legal frame. In this survey, we focus on data-driven AI, as a large part of AI is powered nowadays by (big) data and powerful machine learning algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features such as race, sex, and so forth. This article is categorized under: Commercial, Legal, and Ethical Issues > Fairness in Data Mining Commercial, Legal, and Ethical Issues > Ethical Considerations Commercial, Legal, and Ethical Issues > Legal Issues. © 2020 The Authors. WIREs Data Mining and Knowledge Discovery published by Wiley Periodicals, Inc.

Fact checking is an essential challenge when combating fake news. Identifying documents that agree or disagree with a particular statement (claim) is a core task in this process. In this context, stance detection aims at identifying the position (stance) of a document towards a claim. Most approaches address this task through a 4-class classification model where the class distribution is highly imbalanced. Therefore, they are particularly ineffective in detecting the minority classes (for instance, 'disagree'), even though such instances are crucial for tasks such as fact-checking by providing evidence for detecting false claims. In this paper, we exploit the hierarchical nature of stance classes, which allows us to propose a modular pipeline of cascading binary classifiers, enabling performance tuning on a per step and class basis. We implement our approach through a combination of neural and traditional classification models that highlight the misclassification costs of minority classes. Evaluation results demonstrate state-of-the-art performance of our approach and its ability to significantly improve the classification performance of the important 'disagree' class., Comment: This is a pre-print version of the Journal paper published in J Intell Inf Syst (2021) (Springer). https://rdcu.be/ckLiC

Publicly available social media archives facilitate research in the social sciences and provide corpora for training and testing a wide range of machine learning and natural language processing methods. With respect to the recent outbreak of the Coronavirus disease 2019 (COVID-19), online discourse on Twitter reflects public opinion and perception related to the pandemic itself as well as mitigating measures and their societal impact. Understanding such discourse, its evolution, and interdependencies with real-world events or (mis)information can foster valuable insights. On the other hand, such corpora are crucial facilitators for computational methods addressing tasks such as sentiment analysis, event detection, or entity recognition. However, obtaining, archiving, and semantically annotating large amounts of tweets is costly. In this paper, we describe TweetsCOV19, a publicly available knowledge base of currently more than 8 million tweets, spanning October 2019 - April 2020. Metadata about the tweets as well as extracted entities, hashtags, user mentions, sentiments, and URLs are exposed using established RDF/S vocabularies, providing an unprecedented knowledge base for a range of knowledge discovery tasks. Next to a description of the dataset and its extraction and annotation process, we present an initial analysis and use cases of the corpus.

AI-based systems are widely employed nowadays to make decisions that have far-reaching impacts on individuals and society. Their decisions might affect everyone, everywhere and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multi-disciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well-grounded in a legal frame. In this survey, we focus on data-driven AI, as a large part of AI is powered nowadays by (big) data and powerful Machine Learning (ML) algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features like race, sex, etc., Comment: 19 pages, 1 figure

The current de-facto way to query the Web of Data is through the SPARQL protocol, where a client sends queries to a server through a SPARQL endpoint. Contrary to an HTTP server, providing and maintaining a robust and reliable endpoint requires a significant effort that not all publishers are willing or able to make. An alternative query evaluation method is through link traversal, where a query is answered by dereferencing online web resources (URIs) at real time. While several approaches for such a lookup-based query evaluation method have been proposed, there exists no analysis of the types (patterns) of queries that can be directly answered on the live Web, without accessing local or remote endpoints and without a-priori knowledge of available data sources. In this paper, we first provide a method for checking if a SPARQL query (to be evaluated on a SPARQL endpoint) can be answered through zero-knowledge link traversal (without accessing the endpoint), and analyse a large corpus of real SPARQL query logs for finding the frequency and distribution of answerable and non-answerable query patterns. Subsequently, we provide an algorithm for transforming answerable queries to SPARQL-LD queries that bypass the endpoints. We report experimental results about the efficiency of the transformed queries and discuss the benefits and the limitations of this query evaluation method., Comment: Preprint of paper accepted for publication in the 34th ACM/SIGAPP Symposium On Applied Computing (SAC 2019)

Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where the lack of precision on particularly ambiguous mentions often spoils the usefulness of automated disambiguation results in real applications. A priori approximations of the difficulty to link a particular entity mention can facilitate flagging of critical cases as part of semi-automated EL systems, while detecting latent factors that affect the EL performance, like corpus-specific features, can provide insights on how to improve a system based on the special characteristics of the underlying corpus. In this paper, we first introduce a consensus-based method to generate difficulty labels for entity mentions on arbitrary corpora. The difficulty labels are then exploited as training data for a supervised classification task able to predict the EL difficulty of entity mentions using a variety of features. Experiments over a corpus of news articles show that EL difficulty can be estimated with high accuracy, revealing also latent features that affect EL performance. Finally, evaluation results demonstrate the effectiveness of the proposed method to inform semi-automated EL pipelines., Comment: Preprint of paper accepted for publication in the 34th ACM/SIGAPP Symposium On Applied Computing (SAC 2019)

How did the popularity of the Greek Prime Minister evolve in 2015? How did the predominant sentiment about him vary during that period? Were there any controversial sub-periods? What other entities were related to him during these periods? To answer these questions, one needs to analyze archived documents and data about the query entities, such as old news articles or social media archives. In particular, user-generated content posted in social networks, like Twitter and Facebook, can be seen as a comprehensive documentation of our society, and thus meaningful analysis methods over such archived data are of immense value for sociologists, historians and other interested parties who want to study the history and evolution of entities and events. To this end, in this paper we propose an entity-centric approach to analyze social media archives and we define measures that allow studying how entities were reflected in social media in different time periods and under different aspects, like popularity, attitude, controversiality, and connectedness with other entities. A case study using a large Twitter archive of four years illustrates the insights that can be gained by such an entity-centric and multi-aspect analysis., Comment: This is a preprint of an article accepted for publication in the International Journal on Digital Libraries (2018)

Archived collections of documents (like newspaper and web archives) serve as important information sources in a variety of disciplines, including Digital Humanities, Historical Science, and Journalism. However, the absence of efficient and meaningful exploration methods still remains a major hurdle in the way of turning them into usable sources of information. A semantic layer is an RDF graph that describes metadata and semantic information about a collection of archived documents, which in turn can be queried through a semantic query language (SPARQL). This allows running advanced queries by combining metadata of the documents (like publication date) and content-based semantic information (like entities mentioned in the documents). However, the results returned by such structured queries can be numerous and moreover they all equally match the query. In this paper, we deal with this problem and formalize the task of "ranking archived documents for structured queries on semantic layers". Then, we propose two ranking models for the problem at hand which jointly consider: i) the relativeness of documents to entities, ii) the timeliness of documents, and iii) the temporal relations among the entities. The experimental results on a new evaluation dataset show the effectiveness of the proposed models and allow us to understand their limitations

The Web has evolved to a dominant platform where everyone has the opportunity to express their opinions, to interact with other users, and to debate on emerging events happening around the world. On the one hand, this has enabled the presence of different viewpoints and opinions about a - usually controversial - topic (like Brexit), but at the same time, it has led to phenomena like media bias, echo chambers and filter bubbles, where users are exposed to only one point of view on the same topic. Therefore, there is the need for methods that are able to detect and explain the different viewpoints. In this paper, we propose a graph partitioning method that exploits social interactions to enable the discovery of different communities (representing different viewpoints) discussing about a controversial topic in a social network like Twitter. To explain the discovered viewpoints, we describe a method, called Iterative Rank Difference (IRD), which allows detecting descriptive terms that characterize the different viewpoints as well as understanding how a specific term is related to a viewpoint (by detecting other related descriptive terms). The results of an experimental evaluation showed that our approach outperforms state-of-the-art methods on viewpoint discovery, while a qualitative analysis of the proposed IRD method on three different controversial topics showed that IRD provides comprehensive and deep representations of the different viewpoints.

Entity relatedness has emerged as an important feature in a plethora of applications such as information retrieval, entity recommendation and entity linking. Given an entity, for instance a person or an organization, entity relatedness measures can be exploited for generating a list of highly-related entities. However, the relation of an entity to some other entity depends on several factors, with time and context being two of the most important ones (where, in our case, context is determined by a particular corpus). For example, the entities related to the International Monetary Fund are different now compared to some years ago, while these entities also may highly differ in the context of a USA news portal compared to a Greek news portal. In this paper, we propose a simple but flexible model for entity relatedness which considers time and entity aware word embeddings by exploiting the underlying corpus. The proposed model does not require external knowledge and is language independent, which makes it widely useful in a variety of applications.

Web archiving is the process of collecting portions of the Web to ensure that the information is preserved for future exploitation. However, despite the increasing number of web archives worldwide, the absence of efficient and meaningful exploration methods still remains a major hurdle in the way of turning them into a usable and useful information source. In this paper, we focus on this problem and propose an RDF/S model and a distributed framework for building semantic profiles ("layers") that describe semantic information about the contents of web archives. A semantic layer allows describing metadata information about the archived documents, annotating them with useful semantic information (like entities, concepts and events), and publishing all this data on the Web as Linked Data. Such structured repositories offer advanced query and integration capabilities, and make web archives directly exploitable by other systems and tools. To demonstrate their query capabilities, we build and query semantic layers for three different types of web archives. An experimental evaluation showed that a semantic layer can answer information needs that existing keyword-based systems are not able to sufficiently satisfy., Comment: This is a preprint of an article accepted for publication in the International Journal on Digital Libraries (2018)

Archived collections of documents (like newspaper archives) serve as important information sources for historians, journalists, sociologists and other interested parties. Semantic Layers over such digital archives allow describing and publishing metadata and semantic information about the archived documents in a standard format (RDF), which in turn can be queried through a structured query language (e.g., SPARQL). This enables to run advanced queries by combining metadata of the documents (like publication date) and content-based semantic information (like entities mentioned in the documents). However, the results returned by structured queries can be numerous and also they all equally match the query. Thus, there is the need to rank these results in order to promote the most important ones. In this paper, we focus on this problem and propose a ranking model that considers and combines: i) the relativeness of documents to entities, ii) the timeliness of documents, and iii) the relations among the entities.

Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.

The federated query extension of SPARQL 1.1 allows executing queries distributed over different SPARQL endpoints. SPARQL-LD is a recent extension of SPARQL 1.1 which enables to directly query any HTTP web source containing RDF data, like web pages embedded with RDFa, JSON-LD or Microformats, without requiring the declaration of named graphs. This makes possible to query a large number of data sources (including SPARQL endpoints, online resources, or even Web APIs returning RDF data) through a single one concise query. However, not optimal formulation of SPARQL 1.1 and SPARQL-LD queries can lead to a large number of calls to remote resources which in turn can lead to extremely high query execution times. In this paper, we address this problem and propose a set of query reordering methods which make use of heuristics to reorder a set of SERVICE graph patterns based on their restrictiveness, without requiring the gathering and use of statistics from the remote sources. Such a query optimization approach is widely applicable since it can be exploited on top of existing SPARQL 1.1 and SPARQL-LD implementations. Evaluation results show that query reordering can highly decrease the query-execution time, while a method that considers the number and type of unbound variables and joins achieves the optimal query plan in 88% of the cases.

Artificial Intelligence (AI)‐based systems are widely employed nowadays to make decisions that have far‐reaching impact on individuals and society. Their decisions might affect everyone, everywhere, and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training, and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multidisciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well‐grounded in a legal frame. In this survey, we focus on data‐driven AI, as a large part of AI is powered nowadays by (big) data and powerful machine learning algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features such as race, sex, and so forth.

Artificial Intelligence (AI)‐based systems are widely employed nowadays to make decisions that have far‐reaching impact on individuals and society. Their decisions might affect everyone, everywhere, and anytime, entailing concerns about potential human rights issues. Therefore, it is necessary to move beyond traditional AI algorithms optimized for predictive performance and embed ethical and legal principles in their design, training, and deployment to ensure social good while still benefiting from the huge potential of the AI technology. The goal of this survey is to provide a broad multidisciplinary overview of the area of bias in AI systems, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well‐grounded in a legal frame. In this survey, we focus on data‐driven AI, as a large part of AI is powered nowadays by (big) data and powerful machine learning algorithms. If otherwise not specified, we use the general term bias to describe problems related to the gathering or processing of data that might result in prejudiced decisions on the bases of demographic features such as race, sex, and so forth.