Browsing by Author "Rantala, Heikki"

Now showing 1 - 20 of 33
  • Thumbnail Image
    Item
    Akatemiasampo-portaali ja -datapalvelu henkilöiden ja henkilöryhmien historialliseen tutkimukseen (AcademySampo Portal and Data Service for Biographical and Prosopographical Research)
    (Informaatiotutkimuksen yhdistys, 2021-05-01) Hyvönen, Eero; Leskinen, Petri; Rantala, Heikki; Ikkala, Esko; Tuominen, Jouni; Tietotekniikan laitos; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Professorship Hyvönen Eero
    AcademySampo – Academic people in Finland 1640–1899 is a portal and a Linked Open Data service on the Semantic Web. AcademySampo contains richly interlinked open data about all people that have got academic education in Finland in 1640–1899. The system is targeted to researchers and the general public for biographical and prosopographical research. This review gives an overview on how AcademySampo can be utilized in practise with its novel digital humanities tools included in the portal and by using the data service via APIs.
  • Thumbnail Image
    Item
    AMMO ontology of Finnish historical occupations
    (RWTH Aachen University, 2019) Koho, Mikko; Gasbarra, Lia; Tuominen, Jouni; Rantala, Heikki; Jokipii, Ilkka; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; Professorship Hyvönen Eero; University of Helsinki
    This paper introduces AMMO Ontology of Finnish Historical Occupations. AMMO is based on thousands of occupational labels extracted from three Finnish military historical datasets of the early 20th century: the first consists of the ca. 40 000 war-related death records around the time of the Finnish Civil War (1914–1922); the second consists of the ca. 95 000 death records of Finnish soldiers in the Second World War (1939–1945); the third contains the ca. 4500 records of Finnish prisoners of war in the Soviet Union during the WW2. Our goal from a Digital Humanities perspective is to use AMMO to study military history and these datasets based on the occupation and social status of the soldiers. AMMO will also be used as a component for faceted search and semantic recommendation in two semantic portals for Finnish military history. AMMO is aligned with the international historical occupation classification HISCO and with a modern Finnish occupational classification for international and national interoperability. The ontology is published as Linked Open Data in an ontology service.
  • Thumbnail Image
    Item
    Analyzing the Lives of Finnish Academic People 1640-1899 in Nordic and Baltic Countries: AcademySampo Data Service and Portal
    (RWTH Aachen University, 2022) Leskinen, Petri; Hyvönen, Eero; Rantala, Heikki; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML)
    This paper shows how the newly published Linked Open Data (LOD) service and semantic portal “AcademySampo - Finnish Academic People 1640-1899” can be used for Digital Humanities (DH) research. The original primary data, based on some ten man-years of digitization work, covers a significant part of the Finnish university history based on the student registries in 1640-1852 and 1853-1899. They contain biographical descriptions of 28 000 students of the University of Helsinki, originally the Royal Academy of Turku. AcademySampo also sheds light to the academic history of Sweden and Baltic countries through their shared history with Finland in the larger Swedish Empire. The Finnish student registries have been widely used by genealogists and historians by close reading. We argue that unprecedented new possibilities for DH research are now enabled by using AcademySampo: the underlying knowledge graph can be accessed and analyzed using Semantic Web technologies and tools and with the ready-to-use data-analytic tools of the portal. Examples of data-analysis are presented by using the AcademySampo system for studying migrations of students in Finland, Sweden, Russia, and Estonia, history of student nations, inheritance of vocations and social classes, lengths of family lines of students, and network analyses of students. Related analyses have been made before using biographical dictionaries but not for academic history and student registries.
  • Thumbnail Image
    Item
    Biografiasampo yhdistää ja rikastaa suomalaiset elämäkerrat linkitettynä datana semanttisessa webissä (Biographysampo links and enriches Finnish biographies as linked data on the Semantic Web
    (Informaatiotutkimuksen yhdistys, 2021-06-01) Hyvönen, Eero; Leskinen, Petri; Tamper, Minna; Rantala, Heikki; Ikkala, Esko; Tuominen, Jouni; Keravuori, Kirsi; Tietotekniikan laitos; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Professorship Hyvönen Eero; Finnish Literature Society
    Informaatiotutkimuksen tavoitteena on kehittää uusia tapoja tuottaa, organisoida ja käyttää tietoa sekä yksilöiden että organisaatioiden näkökulmasta. Tässä katsauksessa esitellään kulttuurihistoriallisen tiedon tuottajia ja käyttäjiä palvelevan ns. Sampo-mallin sovellus Biografiasampo kansalaisille, digitaalisten ihmistieteiden tutkijoille ja uusien sovellusten kehittäjille. Biografiasammon kunnianhimoisena tavoitteena on käynnistää uusi aikakausi elämäkertakokoelmien julkaisemisessa ja käyttämisessä verkossa semanttisen webin teknologioita ja linkitetyn avoimen datan julkaisuperiaatteita hyödyntäen. Innovaationa on luoda kieliteknologian, tekoälyn ja semanttisen webin teknologioiden avulla elämäkertojen teksteistä ja niihin eri lähteissä liittyvistä tietokannoista tietämysverkko (knowledge graph) osana kansallista tietoinfrastruktuuria. Sovelluksen ydinaineistona ovat Kansallisbiografia ja muut Suomalaisen Kirjallisuuden Seuran toimittamat ja julkaisemat pienoiselämäkerrat, yhteensä 13 100 elämäntarinaa, joita on kirjoittanut 980 suomalaista tutkijaa maamme suurimmaksi sanotussa historiantutkimuksen hankkeessa. Elämäkerroista louhittua dataa on rikastettu automaattisen loogisen päättelyn avulla ja linkittämällä sitä 16 muuhun tietolähteeseen. Tietämysverkko on julkaistu linkitetyn avoimen datan Linked Data Finland -palvelussa. Datapalvelun avulla on toteutettu seitsemästä sovellusnäkymästä koostuva älykäs, avoin ja maksuton verkkopalvelu biografiasampo.fi, jolla on ollut noin 50 000 käyttäjää. Sekä järjestelmän elämäkerrat että niistä louhittu data ovat avoimesti käytettävissä datapalveluna Linked Data Finland -alustalla.
  • No Thumbnail Available
    Item
    BiographySampo – Publishing and enriching biographies on the semantic web for digital humanities research
    (Springer, 2019-06-02) Hyvönen, Eero; Leskinen, Petri; Tamper, Minna; Rantala, Heikki; Ikkala, Esko; Tuominen, Jouni; Keravuori, Kirsi; Department of Computer Science; Zaveri, Amrapali; Gray, Alasdair J.G.; Hammar, Karl; Hitzler, Pascal; Lopez, Vanessa; Janowicz, Krzysztof; Fernández, Miriam; Haller, Armin; Professorship Hyvönen Eero; Finnish Literature Society
    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.
  • Thumbnail Image
    Item
    Building a Linked Open Data Portal of War Victims in Finland 1914-1922
    (CEUR, 2020-10) Rantala, Heikki; Jokipii, Ilkka; Koho, Mikko; Ikkala, Esko; Tuominen, Jouni; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; University of Helsinki
    This paper presents results from a project that publishes data about the war victims in Finland in 1914–22 as a Linked Open Data service and a portal of tools called WARVICTIMSAMPO 1914–22 to explore and analyze the data. At the same time, the data is extended with new information and cleaned from mistakes when found. The project is based on the database War Victims of Finland 1914–22 (“Sotasurmat 1914–22”) of the National Archives of Finland and related data compiled during the project. This database contains some 40000 death records, most of which are due to the Finnish Civil War but some are related to the First World War and the Kindred Nations Wars. In addition to the war victims, our data includes information about 1200 battles of the Civil War and various prisoner camps. A key novelty of WARVICTIMSAMPO 1914–22 is the integration of ready-to-use Digital Humanities tooling with the data service, which allows, e.g., studying information about wider prosopographical groups in addition to individual victims. We show by examples how using the tools of the portal the data can be better explored and analyzed for research and education purposes.
  • Thumbnail Image
    Item
    Building Lightweight Ontologies for Faceted Search with Named Entity Recognition: Case WarMemoirSampo
    (RWTH Aachen University, 2022-08-11) Koho, Mikko; Leal, Rafael; Ikkala, Esko; Tamper, Minna; Rantala, Heikki; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML)
    This paper discusses building lightweight ontologies for faceted search user interfaces with Named Entity Recognition (NER) from textual data. This is studied in the context of building a Knowledge Graph for the textual indexing of interview videos in the in-use WarMemoirSampo system, consisting of a Linked Open Data service and an open semantic web portal for contextualized video viewing. It is shown that state-of-the-art NER tools are able to find entities from textual data and categorize them with high enough recall and precision to be useful for building facet ontologies, without involving considerable manual domain ontology engineering. To enable entity disambiguation and to be able to show relevant contextual information and useful links for the users of the portal, also Named Entity Linking techniques are employed.
  • No Thumbnail Available
    Item
    Citizen science archaeological finds on the Semantic Web: The FindSampo framework
    (Cambridge University Press, 2021-08) Hyvönen, Eero; Rantala, Heikki; Ikkala, Esko; Koho, Mikko; Tuominen, Jouni; Anafi, Babatunde; Thomas, Suzie; Wessman, Anna; Oksanen, Eljas; Rohiola, Ville; Kuitunen, Jutta; Ryyppö, Minna; Department of Computer Science; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Professorship Hyvönen Eero; Department of Computer Science; University of Helsinki; Finnish Heritage Agency
    FindSampo fosters collecting, sharing, publishing and studying archaeological finds discovered by the public. The framework includes the following: a mobile find-reporting system; a semantic portal for researchers, the public and collection managers to use; and a Linked Open Data service for creating custom data analyses and for application developers.
  • Thumbnail Image
    Item
    Constellations of Correspondence: a Linked Data Service and Portal for Studying Large and Small Networks of Epistolary Exchange in the Grand Duchy of Finland
    (RWTH Aachen University, 2022) Tuominen, Jouni; Koho, Mikko; Pikkanen, Ilona; Drobac, Senka; Enqvist, Johanna; Hyvönen, Eero; La Mela, Matti; Leskinen, Petri; Paloposki, Hanna Leena; Rantala, Heikki; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Finnish Literature Society; University of Helsinki; Uppsala University
    This paper presents the vision of aggregating, harmonizing, and publishing letter catalog metadata (information e.g. of senders, receivers and datings of letters) from cultural heritage (CH) institutions in Finland as a single reconciled Linked Open Data (LOD) service and a semantic portal providing data analytical tools for researchers. The research is conducted as part of the consortium research project Constellations of Correspondence (CoCo). The target of the project is to study - for the first time - scattered, heterogeneous epistolary metadata regarding the period of the Grand Duchy of Finland (1809-1917) as one, integrated dataset and make it interoperable and available. This will enable scholars to ask ambitious research questions in the field of computer science and to conduct empirical, bottom-up case studies e.g. on epistolary culture, communicative networks, and heritagization processes. This paper discusses one of the first datasets acquired by the project, the letter collection of the Board of the Finnish Art Society (1846-1901), provided by the Finnish National Gallery, which contains details of c. 1150 letters sent or received by c. 400 actors.
  • Thumbnail Image
    Item
    Developing a tool for information retrieval and research purposes utilizing BookSampo data
    (2023-03-20) Ahola, Annastiina; Rantala, Heikki; Perustieteiden korkeakoulu; Hyvönen, Eero
    The goal of this thesis was to develop a new tool for information retrieval and research purposes based on the BookSampo data set. The current BookSampo portal uses Linked Data but offers limited search capabilities to the user that do not fully utilize the possibilities of Linked Data. The goal of the new portal was to offer the users both ways to visualize the data as well as a facet-based search, where the user could search and filter the result data set using different facets. The portal was developed using the Sampo Model based Sampo-UI framework that makes it possible to build new semantic portals without requiring a lot of actual programming work. Developing new semantic portals using the Sampo-UI framework is based on editing configuration files that define the wanted components as well as the data location using a SPARQL endpoint. The data used in the portal was the BookSampo dataset, the quality of which was also assessed during the development process. The final product is a Sampo-UI based semantic portal that uses unmodified BookSampo data, which was assessed to be of good quality considering the sheer volume of the data set. The portal offers the user five different perspectives that can be used for looking at and searching for data. The perspectives have their own visualizations developed for them based on the annotation coverage of the data that can be used for viewing the data in different formats, e.g., as a chart or on a map. Sampo-UI framework fit the purpose well and makes it possible to develop the portal easily further in the future. The BookSampo data has and will be receiving the needed fixes, after which it could be published to public use and then improved based on the feedback received from users.
  • Thumbnail Image
    Item
    Digital Humanities and Military History: Analyzing Casualties of the WarSampo Knowledge Graph
    (RWTH Aachen University, 2022) Koho, Mikko; Rantala, Heikki; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML)
    This paper shows how various prosopographical phenomena can be highlighted and visualized in the WarSampo Knowledge Graph that contains rich data about Finland in the Second World War as Linked Open Data, including detailed metadata of more than 100 000 people. WarSampo Portal contains tools for simple prosopographical data analysis of the person registers, and accessing the SPARQL endpoint directly opens up further possibilities in using the ontology infrastructure for enhanced information retrieval and pursuing digital humanities studies. This paper overviews of these possibilities of WarSampo, and presents examples of how it, and by extension Linked Data more generally, can be used to created data analyses to support historical research.
  • Thumbnail Image
    Item
    Digital Humanities Solutions for pan-European Numismatic and Archaeological Heritage Based on Linked Open Data
    (RWTH Aachen University, 2022) Oksanen, Eljas; Rantala, Heikki; Tuominen, Jouni; Lewis, Michael; Wigg-Wolf, David; Ehrnsten, Frida; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); University of Helsinki; British Museum; Deutsches Archäologisches Institut; National Museum of Finland
    This paper discusses current challenges in archaeological cultural heritage data management and presents the interdisciplinary research project DigiNUMA. The project investigates solutions in data harmonisation and dissemination of pan-European cultural heritage through an interdisciplinary and cross-sectoral project in Digital Humanities, semantic computing, participatory heritage, museum collections management and archaeological/numismatic studies. Using Finnish and English numismatic data as a test case, DigiNUMA creates ontological infrastructure and a proof-of-concept data model for finely-grained Linked Open Data (LOD) harmonisation across national and international databases for cultural heritage data, and tests it through a broad suite of Digital Humanities analyses.
  • Thumbnail Image
    Item
    Finding and explaining relations in a biographical knowledge graph based on life events : Case BiographySampo
    (RWTH Aachen University, 2023) Rantala, Heikki; Hyvönen, Eero; Tuominen, Jouni; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML)
    This paper presents a knowledge-based approach for finding and explaining “interesting” semantic relations between persons and places in a knowledge graph. As a case study we use the BiographySampo knowledge graph which includes life events extracted from the short biographies of 13 100 prominent historical persons in Finland. We use SPARQL CONSTRUCT queries to extract connections and create human readable explanations based on the events in the knowledge graph, and then offer faceted search tools to search and filter the connections. The results can then be visualized using various charts and maps.
  • No Thumbnail Available
    Item
    FindSampo: A Linked Data Based Portal and Data Service for Analyzing and Disseminating Archaeological Object Finds
    (2022-05-31) Rantala, Heikki; Ikkala, Esko; Rohiola, Ville; Koho, Mikko; Tuominen, Jouni; Oksanen, Eljas; Wessman, Anna; Hyvönen, Eero; Department of Computer Science; Groth, Paul; Vidal, Maria-Esther; Suchanek, Fabian; Szekley, Pedro; Kapanipathi, Pavan; Pesquita, Catia; Skaf-Molli, Hala; Tamper, Minna; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Finnish Heritage Agency; University of Helsinki; University Museum of Bergen
    This paper presents the FindSampo system for analyzing and disseminating archaeological object finds made by the public. The system is based on Linked Open Data (LOD), and consists of a web portal and an open data service. The underlying knowledge graph contains data of some 3000 archaeological object finds catalogued in the archaeological collection of the Finnish Heritage Agency (FHA) from 2015 to 2020. The portal and LOD service have been open to public use since May 2021.
  • No Thumbnail Available
    Item
    Harmonizing and Using Numismatic Linked Data in Digital Humanities Research and Application Development: Case DigiNUMA
    (Springer, 2022-07-20) Rantala, Heikki; Oksanen, Eljas; Hyvönen, Eero; Department of Computer Science; Groth, Paul; Rula, Anisa; Schneider, Jodi; Tiddi, Ilaria; Simperl, Elena; Alexopoulos, Panos; Hoekstra, Rinke; Alam, Mehwish; Dimou, Anastasia; Tamper, Minna; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); University of Helsinki
    This paper outlines the ongoing work of the DigiNUMA project for creating solutions in data harmonisation, analysis, and dissemination of pan-European archaeological and numismatic Cultural Heritage, using linked data and semantic web technologies. The project focuses on Viking Age (800–1150 AD) Finnish and English numismatic data as a case study. A broader context is gained by research into harmonizing collection data of the National Museum of Finland, the British Museum, and the Fitzwilliam Museum in Cambridge for compatibility with the international Nomisma.org ontology, and by creating tools that can be used to work with other Nomisma.org datasets.
  • Thumbnail Image
    Item
    How to create easily a data analytic semantic portal on top of a SPARQL endpoint: introducing the configurable Sampo-UI framework
    (RWTH Aachen University, 2023) Rantala, Heikki; Ahola, Annastiina; Ikkala, Esko; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML)
  • No Thumbnail Available
    Item
    How to Search and Contextualize Scenes inside Videos for Enriched Watching Experience: Case Stories of the Second World War Veterans
    (Springer, 2022-07-20) Hyvönen, Eero; Ikkala, Esko; Koho, Mikko; Leal, Rafael; Rantala, Heikki; Tamper, Minna; Department of Computer Science; Groth, Paul; Rula, Anisa; Schneider, Jodi; Tiddi, Ilaria; Simperl, Elena; Alexopoulos, Panos; Hoekstra, Rinke; Alam, Mehwish; Dimou, Anastasia; Tamper, Minna; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Professorship Hyvönen Eero
    This demo paper demonstrates the idea of publishing and watching videos on the Semantic Web. An in-use application, WarMemoirSampo, is presented that enables scene segments in videos to be searched by their semantic content. While watching a video, additional contextual information is provided dynamically. The system is based on a SPARQL endpoint whose knowledge graph has been extracted automatically from timestamped natural language descriptions of the video contents.
  • Thumbnail Image
    Item
    Knowledge-based relation discovery in cultural heritage knowledge graphs
    (RWTH Aachen University, 2019) Hyvönen, Eero; Rantala, Heikki; Department of Computer Science; Professorship Hyvönen Eero
    This paper presents a new knowledge-based approach for finding serendipitous semantic relations between resources in a knowledge graph. The idea is to characterize the notion of “interesting connection” in terms of generic ontological explanation patterns that are applied to an underlying linked data repository to instantiate connections. In this way, 1) semantically uninteresting connections can be ruled out effectively, and 2) natural language explanations about the connections can be created for the end-user. The idea has been implemented and tested based on a knowledge graph of biographical data extracted from the biographies of 13 000 prominent historical persons in Finland, enriched by data linking to collection databases of museums, libraries, and archives. The demonstrator is in use as part of the BiographySampo portal of interlinked biographies.
  • No Thumbnail Available
    Item
    Knowledge-based Relational Search in Cultural Heritage Linked Data
    (Oxford University Press, 2021-10) Hyvönen, Eero; Rantala, Heikki; Department of Computer Science; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); Professorship Hyvönen Eero
    This article presents a new knowledge-based approach for finding interesting semantic relations between resources in a knowledge graph (KG). The idea is to characterize the notion of ‘interesting connection’ in terms of generic ontological explanation patterns that are applied to an underlying linked data repository to instantiate connections. In this way, (1) semantically uninteresting connections can be ruled out effectively and (2) natural language explanations about the connections can be created for the end-user. The idea has been implemented and tested based on a KG of biographical data extracted from the life stories of 13,144 prominent historical persons in Finland, enriched by data linking to collection databases of museums, libraries, and archives. The demonstrator is in use as part of the BiographySampo portal of interlinked biographies.
  • Thumbnail Image
    Item
    The Laborious Cleaning: Acquiring and Transforming 19th-Century Epistolary Metadata
    (University of Oslo, 2023) Drobac, Senka; Enqvist, Johanna; Leskinen, Petri; Wahjoe, Muhammad; Rantala, Heikki; Koho, Mikko; Pikkanen, Ilona; Jauhianinen, Iida; Tuominen, Jouni; Paloposki, Hanna Leena; La Mela, Matti; Hyvönen, Eero; Department of Computer Science; Professorship Hyvönen Eero; Computer Science Professors; Computer Science - Artificial Intelligence and Machine Learning (AIML); University of Helsinki; Department of Computer Science; Finnish Literature Society
    The paper documents the process of collecting, consolidating, and publishing epistolary metadata from Finnish cultural heritage organizations to create an archive for bottom-up analyses of 19th-century epistolary culture. We describe and discuss the data survey that was conducted to gather information about available letter collections across Finland, as well as the cleaning and harmonizing of over 350,000 letters from twelve different sources in various digital formats. We have also developed a data model that combines event-based and letter-based aspects of the metadata. Furthermore, the paper contributes to the ongoing discussion of the initial phases of data-intensive research and the importance of discussing the labor of cleaning data. We believe that our experiences described in this paper can have wider significance for other digital humanities projects in Europe.