Traditionally, humanities scholars carrying out research on a specific or on multiple literary work(s) are interested in the analysis of related texts or text passages. But the digital age has opened possibilities for scholars to enhance their traditional workflows. Enabled by digitization projects, humanities scholars can nowadays reach a large number of digitized texts through web portals such as Google Books or Internet Archive. Digital editions exist also for ancient texts; notable examples are PHI Latin Texts and the Perseus Digital Library. This shift from reading a single book “on paper” to the possibility of browsing many digital texts is one of the origins and principal pillars of the digital humanities domain, which helps developing solutions to handle vast amounts of cultural heritage data – text being the main data type. In contrast to the traditional methods, the digital humanities allow to pose new research questions on cultural heritage datasets. Some of these questions can be answered with existent algorithms and tools provided by the computer science domain, but for other humanities questions scholars need to formulate new methods in collaboration with computer scientists. Developed in the late 1980s, the digital humanities primarily focused on designing standards to represent cultural heritage data such as the Text Encoding Initiative (TEI) for texts, and to aggregate, digitize and deliver data. In the last years, visualization techniques have gained more and more importance when it comes to analyzing data. For example, Saito introduced her 2010 digital humanities conference paper with: “In recent years, people have tended to be overwhelmed by a vast amount of information in various contexts. Therefore, arguments about ’Information Visualization’ as a method to make information easy to comprehend are more than understandable.” A major impulse for this trend was given by Franco Moretti. In 2005, he published the book “Graphs, Maps, Trees”, in which he proposes so-called distant reading approaches for textual data that steer the traditional way of approaching literature towards a completely new direction. Instead of reading texts in the traditional way – so-called close reading –, he invites to count, to graph and to map them. In other words, to visualize them. This dissertation presents novel close and distant reading visualization techniques for hitherto unsolved problems. Appropriate visualization techniques have been applied to support basic tasks, e.g., visualizing geospatial metadata to analyze the geographical distribution of cultural heritage data items or using tag clouds to illustrate textual statistics of a historical corpus. In contrast, this dissertation focuses on developing information visualization and visual analytics methods that support investigating research questions that require the comparative analysis of various digital humanities datasets. We first take a look at the state-of-the-art of existing close and distant reading visualizations that have been developed to support humanities scholars working with literary texts. We thereby provide a taxonomy of visualization methods applied to show various aspects of the underlying digital humanities data. We point out open challenges and we present our visualizations designed to support humanities scholars in comparatively analyzing historical datasets. In short, we present (1) GeoTemCo for the comparative visualization of geospatial-temporal data, (2) the two tag cloud designs TagPies and TagSpheres that comparatively visualize faceted textual summaries, (3) TextReuseGrid and TextReuseBrowser to explore re-used text passages among the texts of a corpus, (4) TRAViz for the visualization of textual variation between multiple text editions, and (5) the visual analytics system MusikerProfiling to detect similar musicians to a given musician of interest. Finally, we summarize our and the collaboration experiences of other visualization researchers to emphasize the ingredients required for a successful project in the digital humanities, and we take a look at future challenges in that research field.

Traditionally, humanities scholars carrying out research on a specific or on multiple literary work(s) are interested in the analysis of related texts or text passages. But the digital age has opened possibilities for scholars to enhance their traditional workflows. Enabled by digitization projects, humanities scholars can nowadays reach a large number of digitized texts through web portals such as Google Books or Internet Archive. Digital editions exist also for ancient texts; notable examples are PHI Latin Texts and the Perseus Digital Library. This shift from reading a single book “on paper” to the possibility of browsing many digital texts is one of the origins and principal pillars of the digital humanities domain, which helps developing solutions to handle vast amounts of cultural heritage data – text being the main data type. In contrast to the traditional methods, the digital humanities allow to pose new research questions on cultural heritage datasets. Some of these questions can be answered with existent algorithms and tools provided by the computer science domain, but for other humanities questions scholars need to formulate new methods in collaboration with computer scientists. Developed in the late 1980s, the digital humanities primarily focused on designing standards to represent cultural heritage data such as the Text Encoding Initiative (TEI) for texts, and to aggregate, digitize and deliver data. In the last years, visualization techniques have gained more and more importance when it comes to analyzing data. For example, Saito introduced her 2010 digital humanities conference paper with: “In recent years, people have tended to be overwhelmed by a vast amount of information in various contexts. Therefore, arguments about ’Information Visualization’ as a method to make information easy to comprehend are more than understandable.” A major impulse for this trend was given by Franco Moretti. In 2005, he published the book “Graphs, Maps, Trees”, in which he proposes so-called distant reading approaches for textual data that steer the traditional way of approaching literature towards a completely new direction. Instead of reading texts in the traditional way – so-called close reading –, he invites to count, to graph and to map them. In other words, to visualize them. This dissertation presents novel close and distant reading visualization techniques for hitherto unsolved problems. Appropriate visualization techniques have been applied to support basic tasks, e.g., visualizing geospatial metadata to analyze the geographical distribution of cultural heritage data items or using tag clouds to illustrate textual statistics of a historical corpus. In contrast, this dissertation focuses on developing information visualization and visual analytics methods that support investigating research questions that require the comparative analysis of various digital humanities datasets. We first take a look at the state-of-the-art of existing close and distant reading visualizations that have been developed to support humanities scholars working with literary texts. We thereby provide a taxonomy of visualization methods applied to show various aspects of the underlying digital humanities data. We point out open challenges and we present our visualizations designed to support humanities scholars in comparatively analyzing historical datasets. In short, we present (1) GeoTemCo for the comparative visualization of geospatial-temporal data, (2) the two tag cloud designs TagPies and TagSpheres that comparatively visualize faceted textual summaries, (3) TextReuseGrid and TextReuseBrowser to explore re-used text passages among the texts of a corpus, (4) TRAViz for the visualization of textual variation between multiple text editions, and (5) the visual analytics system MusikerProfiling to detect similar musicians to a given musician of interest. Finally, we summarize our and the collaboration experiences of other visualization researchers to emphasize the ingredients required for a successful project in the digital humanities, and we take a look at future challenges in that research field.

Cultural data can come in various forms and modalities, such as text traditions, artworks, music, crafted objects, or even as intangible heritage such as biographies of people, performing arts, cultural customs and rites. The assignment of metadata to such cultural heritage objects is an important task that people working in galleries, libraries, archives, and museums (GLAM) do on a daily basis. These rich metadata collections are used to categorize, structure, and study collections, but can also be used to apply computational methods. Such computational methods are in the focus of Computational and Digital Humanities projects and research. For the longest time, the digital humanities community has focused on textual corpora, including text mining, and other natural language processing techniques. Although some disciplines of the humanities, such as art history and archaeology have a long history of using visualizations. In recent years, the digital humanities community has started to shift the focus to include other modalities, such as audio-visual data. In turn, methods in machine learning and computer vision have been proposed for the specificities of such corpora. Over the last decade, the visualization community has engaged in several collaborations with the digital humanities, often with a focus on exploratory or comparative analysis of the data at hand. This includes both methods and systems that support classical Close Reading of the material and Distant Reading methods that give an overview of larger collections, as well as methods in between, such as Meso Reading. Furthermore, a wider application of machine learning methods can be observed on cultural heritage collections. But they are rarely applied together with visualizations to allow for further perspectives on the collections in a visual analytics or human-in-the-loop setting. Visual analytics can help in the decision-making process by guiding domain experts through the collection of interest. However, state-of-the-art supervised machine learning methods are often not applicable to the collection of interest due to missing ground truth. One form of ground truth are class labels, e.g., of entities depicted in an image collection, assigned to the individual images. Labeling all objects in a collection is an arduous task when performed manually, because cultural heritage collections contain a wide variety of different objects with plenty of details. A problem that arises with these collections curated in different institutions is that not always a specific standard is followed, so the vocabulary used can drift apart from another, making it difficult to combine the data from these institutions for large-scale analysis. This thesis presents a series of projects that combine machine learning methods with interactive visualizations for the exploratory analysis and labeling of cultural data. First, we define cultural data with regard to heritage and contemporary data, then we look at the state-of-the-art of existing visualization, computer vision, and visual analytics methods and projects focusing on cultural data collections. After this, we present the problems addressed in this thesis and their solutions, starting with a series of visualizations to explore different facets of rap lyrics and rap artists with a focus on text reuse. Next, we engage in a more complex case of text reuse, the collation of medieval vernacular text editions. For this, a human-in-the-loop process is presented that applies word embeddings and interactive visualizations to perform textual alignments on under-resourced languages supported by labeling of the relations between lines and the relations between words. We then switch the focus from textual data to another modality of cultural data by presenting a Virtual Museum that combines interactive visualizations and computer vision in order to explore a collection of artworks. With the lessons learned from the previous projects, we engage in the labeling and analysis of medieval illuminated manuscripts and so combine some of the machine learning methods and visualizations that were used for textual data with computer vision methods. Finally, we give reflections on the interdisciplinary projects and the lessons learned, before we discuss existing challenges when working with cultural heritage data from the computer science perspective to outline potential research directions for machine learning and visual analytics of cultural heritage data.

No description available.

No description available.

No description available.