Cultural heritage data, particularly from colonial contexts, frequently presents an incomplete and biased view, reflecting historical institutional priorities more than contemporary knowledge requirements. Consequently, knowledge graphs derived from these records often contain incomplete, fragmented, and skewed data, including absent attributes or values, missing semantic links, and under-represented perspectives. This work addresses the challenge of knowledge discovery under such limitations, presenting a real-world case study on the provenance research of colonial cultural heritage. We present a task-aware design method for building a tool to facilitate this process. The design approach of this application is rooted in a Knowledge Discovery in Database (KDD) framework and is particularly novel due to its formalisation and operationalisation of three distinct types of semantic association: explicit, abstract, and implicit. These semantic associations, grounded in domain interpretation, are crucial for bridging data gaps where user information needs cannot be directly met by existing data. We further demonstrate how these associations can be effectively communicated through user interface components, enabling users to infer new knowledge. We evaluated the resultant application through a user study among domain experts to assess its efficacy. The evaluation confirms the effectiveness of the tool in enabling new knowledge discovery and reveals opportunities to improve the representation of the underlying data, as users could successfully infer insights even when information was missing or poorly captured in the original data sets.

Abstract The BookSampo Linked Data portal was deployed in 2011 by the Finnish Public Libraries and has today nearly 2 million annual users. Its Linked Data covers virtually all Finnish fiction literature but the data has not been used for data analyses in Digital Humanities. This paper discusses how the Knowledge Graph can be used for literary research in two ways: First, a new BookSampo 2.0 Portal user interface is presented, based on faceted semantic search with seamlessly integrated data‐analytic tools for Digital Humanities research as suggested in the Sampo Model. This application makes it possible to analyze the data without programming skills. Second, the BookSampo SPARQL endpoint API can be accessed directly by SPARQL querying and scripting, using tools such as Jupyter Notebooks. The analysis results presented suggest interesting spatial, temporal, and topical trends in how the Finnish fiction literature has evolved during the last decades. The approach and tools presented in this paper can be used for analyzing literary landscapes developments in other countries as well.

Peer reviewed

Abstract Manuscripts are a crucial form of evidence for research into all aspects of premodern European history and culture, and there are numerous databases devoted to describing them in detail. This descriptive information, however, is typically available only in separate data silos based on incompatible data models and user interfaces. As a result, it has been difficult to study manuscripts comprehensively across these various platforms. To address this challenge, a team of manuscript scholars and computer scientists worked to create “Mapping Manuscript Migrations” (MMM), a semantic portal, and a Linked Open Data service. MMM stands as a successful proof of concept for integrating distinct manuscript datasets into a shared platform for research and discovery with the potential for future expansion. This paper will discuss the major products of the MMM project: a unified data model, a repeatable data transformation pipeline, a Linked Open Data knowledge graph, and a Semantic Web portal. It will also examine the crucial importance of an iterative process of multidisciplinary collaboration embedded throughout the project, enabling humanities researchers to shape the development of a digital platform and tools, while also enabling the same researchers to ask more sophisticated and comprehensive research questions of the aggregated data.

The idea behind Relevance Feedback Search (RFBS) is to build search queries as an iterative and interactive process in which they are gradually refined based on the results of the previous search round. This can be helpful in situations where the end user cannot easily formulate their information needs at the outset as a well-focused query, or more generally as a way to filter and focus search results. This paper concerns (1) a framework that integrates keyword extraction and unsupervised classification into the RFBS paradigm and (2) the application of this framework to the legal domain as a use case. We focus on the Natural Language Processing (NLP) methods underlying the framework and application, where an automatic annotation tool is used for extracting document keywords as ontology concepts, which are then transformed into word embeddings to form vectorial representations of the texts. An unsupervised classification system that employs similar techniques is also used in order to classify the documents into broad thematic classes. This classification functionality is evaluated using two different datasets. As the use case, we describe an application perspective in the semantic portal LawSampo - Finnish Legislation and Case Law on the Semantic Web. This online demonstrator uses a dataset of 82145 sections in 3725 statutes of Finnish legislation and another dataset that comprises 13470 court decisions.

This paper presents a knowledge graph created by transforming the plenary debates of the Parliament of Finland (1907-) into Linked Open Data (LOD). The data, totaling over νm{900 000} speeches, with automatically created semantic annotations and rich ontology-based metadata, are published in a Linked Open Data Service and are used via a SPARQL API and as data dumps. The speech data is part of larger LOD publication FinnParla that also includes prosopographical data about the politicians. The data is being used for studying parliamentary language and culture in Digital Humanities in several universities. To serve a wider variety of users, the entirety of this data was also produced using Parla-CLARIN markup. We present the first publication of all Finnish parliamentary debates as data. Technical novelties in our approach include the use of both Parla-CLARIN and an RDF schema developed for representing the speeches, integration of the data to a new Parliament of Finland Ontology for deeper data analyses, and enriching the data with a variety of external national and international data sources.

This paper argues for making a paradigm shift in publishing and using biographical dictionaries on the web, based on Linked Data. The idea is to provide the user with enhanced reading experience of biographies by enriching contents with data linking and reasoning. In addition, versatile tooling for (1) biographical research of individual persons as well as for (2) prosopographical research on groups of people are provided. To demonstrate and evaluate the new possibilities, we present the semantic portal “BiographySampo – Finnish Biographies on the Semantic Web”. The system is based on a knowledge graph extracted automatically from a collection of 13 100 textual biographies, enriched with data linking to 16 external data sources, and by harvesting external collection data from libraries, museums, and archives. The portal was released in September 2018 for free public use at http://biografiasampo.fi .