@phdthesis{HennyKrahmer2023,
  author    = {Henny-Krahmer, Ulrike},
  title     = {Genre Analysis and Corpus Design: Nineteenth Century Spanish-American Novels (1830-1910)},
  doi       = {10.25972/OPUS-31999},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-319992},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {This work in the field of digital literary stylistics and computational literary studies is concerned with theoretical concerns of literary genre, with the design of a corpus of nineteenth-century Spanish-American novels, and with its empirical analysis in terms of subgenres of the novel. The digital text corpus consists of 256 Argentine, Cuban, and Mexican novels from the period between 1830 and 1910. It has been created with the goal to analyze thematic subgenres and literary currents that were represented in numerous novels in the nineteenth century by means of computational text categorization methods. The texts have been gathered from different sources, encoded in the standard of the Text Encoding Initiative (TEI), and enriched with detailed bibliographic and subgenre-related metadata, as well as with structural information. To categorize the texts, statistical classification and a family resemblance analysis relying on network analysis are used with the aim to examine how the subgenres, which are understood as communicative, conventional phenomena, can be captured on the stylistic, textual level of the novels that participate in them. The result is that both thematic subgenres and literary currents are textually coherent to degrees of 70-90 \%, depending on the individual subgenre constellation, meaning that the communicatively established subgenre classifications can be accurately captured to this extent in terms of textually defined classes. Besides the empirical focus, the dissertation also aims to relate literary theoretical genre concepts to the ones used in digital genre stylistics and computational literary studies as subfields of digital humanities. It is argued that literary text types, conventional literary genres, and textual literary genres should be distinguished on a theoretical level to improve the conceptualization of genre for digital text analysis.},
  subject      = {Gattungstheorie},
  language  = {en}
}
@misc{Prez2021,
  type      = {Master Thesis},
  author    = {Prez, Julia},
  title     = {Immersion als Textfunktion? Sprachliche Praktiken der Spielerlenkung in der Textgrundlage von Computerspielen},
  isbn      = {978-3-945459-35-5},
  issn      = {1864-9238},
  doi       = {10.25972/OPUS-24377},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-243775},
  school      = {Universit{\"a}t W{\"u}rzburg},
  pages     = {101},
  year      = {2021},
  abstract  = {Die Textfunktion beschreibt den vom Emittenten intendierten Effekt eines Textes auf den Rezipienten. Sachb{\"u}cher etwa sind in erster Linie informativ, Werbeanzeigen appellativ, Testamente deklarativ, Vertr{\"a}ge erf{\"u}llen eine Obligationsfunktion und Danksagungen eine Kontaktfunktion. Wie sieht es aber mit Computerspielen aus? K{\"o}nnen diese als Texte auf ihre Textfunktion untersucht werden? Laut den Game Studies ist Immersion das erkl{\"a}rte Ziel der Spielentwickler, wobei Aufmerksamkeitslenkung eine bedeutende Rolle einnimmt. Ist denn Immersion auch linguistisch als Textfunktion nachweisbar? Um dies herauszufinden, werden Computerspiele - gem{\"a}ß dem Textanalyseschema von Brinker, C{\"o}lfen und Pappert \(^8\)2014 - zun{\"a}chst als Texte definiert. Im Rahmen dieser Analyse werden auch Koh{\"a}renz und Koh{\"a}sion untersucht und sprachliche Mittel werden als Indizien betrachtet, die auf die Funktion hinweisen. Im Fokus stehen dabei M{\"u}ndlichkeit und Schriftlichkeit, emotionale Sprache, die Kodierung von Regeln und Herausforderungen sowie Referenzen auf das Interface. Im Speziellen werden Adventure und Role Playing Games (im Offline- und Single Player Modus) als Textsorten untersucht, weil diese Spiele {\"u}blicherweise viel Text enthalten. Zur Textsortenabgrenzung wird zun{\"a}chst ein Spiel genauestens mittels AntConc untersucht, um anschließend das gesamte Korpus (23 Spiele, 70.060 Types, 1.183.536 Tokens) unter Verwendung von LancsBox vergleichend zu analysieren. Zusammenfassend kann diese Masterarbeit als eine der ersten Studien eines vernachl{\"a}ssigten, aber gegenw{\"a}rtigen und an Bedeutung gewinnenden Bereichs linguistischer Forschung betrachtet werden, der Linguistik, Computerspiele und Immersion zu verbinden versucht. Die Hypothese, dass es gewisse sprachliche Praktiken in Computerspiel-Texten gibt, anhand derer der Rezipient beeinflusst und gelenkt wird, um in das Spiel hineinzutauchen, konnte auf Basis des Korpus best{\"a}tigt werden.},
  subject      = {Linguistik},
  language  = {de}
}
@article{AurastGradlPernesetal.2016,
  author    = {Aurast, Anna and Gradl, Tobias and Pernes, Stefan and Pielstr{\"o}m, Steffen},
  title     = {Big Data und Smart Data in den Geisteswissenschaften},
  series = {Bibliothek Forschung und Praxis},
  volume    = {40},
  journal   = {Bibliothek Forschung und Praxis},
  number    = {2},
  issn      = {1865-7648},
  doi       = {10.1515/bfp-2016-0033},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-195237},
  pages     = {200-206},
  year      = {2016},
  abstract  = {Kein Abstract verf{\"u}gbar.},
  language  = {de}
}
@phdthesis{Krug2020,
  author    = {Krug, Markus},
  title     = {Techniques for the Automatic Extraction of Character Networks in German Historic Novels},
  doi       = {10.25972/OPUS-20918},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-209186},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {Recent advances in Natural Language Preprocessing (NLP) allow for a fully automatic extraction of character networks for an incoming text. These networks serve as a compact and easy to grasp representation of literary fiction. They offer an aggregated view of the text, which can be used during distant reading approaches for the analysis of literary hypotheses. In their core, the networks consist of nodes, which represent literary characters, and edges, which represent relations between characters. For an automatic extraction of such a network, the first step is the detection of the references of all fictional entities that are of importance for a text. References to the fictional entities appear in the form of names, noun phrases and pronouns and prior to this work, no components capable of automatic detection of character references were available. Existing tools are only capable of detecting proper nouns, a subset of all character references. When evaluated on the task of detecting proper nouns in the domain of literary fiction, they still underperform at an F1-score of just about 50\%. This thesis uses techniques from the field of semi-supervised learning, such as Distant supervision and Generalized Expectations, and improves the results of an existing tool to about 82\%, when evaluated on all three categories in literary fiction, but without the need for annotated data in the target domain. However, since this quality is still not sufficient, the decision to annotate DROC, a corpus comprising 90 fragments of German novels was made. This resulted in a new general purpose annotation environment titled as ATHEN, as well as annotated data that spans about 500.000 tokens in total. Using this data, the combination of supervised algorithms and a tailored rule based algorithm, which in combination are able to exploit both - local consistencies as well as global consistencies - yield an algorithm with an F1-score of about 93\%. This component is referred to as the Kallimachos tagger. A character network can not directly display references however, instead they need to be clustered so that all references that belong to a real world or fictional entity are grouped together. This process widely known as coreference resolution is a hard problem in the focus of research for more than half a century. This work experimented with adaptations of classical feature based machine learning, with a dedicated rule based algorithm and with modern techniques of Deep Learning, but no approach can surpass 55\% B-Cubed F1, when evaluated on DROC. Due to this barrier, many researchers do not use a fully-fledged coreference resolution when they extract character networks, but only focus on a more forgiving subset- the names. For novels such as Alice's Adventures in Wonderland by Lewis Caroll, this would however only result in a network in which many important characters are missing. In order to integrate important characters into the network that are not named by the author, this work makes use of automatic detection of speaker and addressees for direct speech utterances (all entities involved in a dialog are considered to be of importance). This problem is by itself not an easy task, however the most successful system analysed in this thesis is able to correctly determine the speaker to about 85\% of the utterances as well as about 65\% of the addressees. This speaker information can not only help to identify the most dominant characters, but also serves as a way to model the relations between entities. During the span of this work, components have been developed to model relations between characters using speaker attribution, using co-occurrences as well as by the usage of true interactions, for which yet again a dataset was annotated using ATHEN. Furthermore, since relations between characters are usually typed, a component for the extraction of a typed relation was developed. Similar to the experiments for the character reference detection, a combination of a rule based and a Maximum Entropy classifier yielded the best overall results, with the extraction of family relations showing a score of about 80\% and the quality of love relations with a score of about 50\%. For family relations, a kernel for a Support Vector Machine was developed that even exceeded the scores of the combined approach but is behind on the other labels. In addition, this work presents new ways to evaluate automatically extracted networks without the need of domain experts, instead it relies on the usage of expert summaries. It also refrains from the uses of social network analysis for the evaluation, but instead presents ranked evaluations using Precision@k and the Spearman Rank correlation coefficient for the evaluation of the nodes and edges of the network. An analysis using these metrics showed, that the central characters of a novel are contained with high probability but the quality drops rather fast if more than five entities are analyzed. The quality of the edges is mainly dominated by the quality of the coreference resolution and the correlation coefficient between gold edges and system edges therefore varies between 30 and 60\%. All developed components are aggregated alongside a large set of other preprocessing modules in the Kallimachos pipeline and can be reused without any restrictions.},
  subject      = {Textanalyse},
  language  = {en}
}
@article{Schoech2016,
  author    = {Sch{\"o}ch, Christof},
  title     = {Ein digitales Textformat f{\"u}r die Literaturwissenschaften. Die Richtlinien der Text Encoding Initiative und ihr Nutzen f{\"u}r Textedition und Textanalyse},
  series = {Romanische Studien},
  volume    = {4},
  journal   = {Romanische Studien},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-171351},
  pages     = {325-364},
  year      = {2016},
  abstract  = {Die stetig voranschreitende Digitalisierung literarischer Texte verschiedenster Sprachen, Epochen und Gattungen stellt die Literaturwissenschaften immer wieder vor die Frage, wie sie diese Entwicklung mitgestalten und zu ihrem Vorteil nutzen k{\"o}nnen. Dabei ist digital nicht gleich digital, sondern es existiert eine Vielzahl sehr unterschiedlicher, digitaler Repr{\"a}sentationsformen von Text. Nur wenige dieser Repr{\"a}sentationsformen werden literaturwissenschaftlichen Anforderungen tats{\"a}chlich gerecht, darunter diejenige, die den Richtlinien der Text Encoding Initiative folgt. Der vorliegende Beitrag vergleicht zun{\"a}chst einige derzeit g{\"a}ngige digitale Repr{\"a}sentationsformen von Text. F{\"u}r literaturwissenschaftliche Forschung besonders geeignet erweist sich hierbei eine Repr{\"a}sentationsform, die den Richtlinien der Text Encoding Initiative folgt. Daher informiert der Beitrag anschließend {\"u}ber deren Nutzen f{\"u}r die literaturwissenschaftliche Arbeit, sowohl im Bereich der wissenschaftlichen Textedition als auch im Bereich der Analyse und Interpretation von Texten. Nur wenn die Literaturwissenschaften in ihrer Breite den Nutzen von offenen, expressiven, flexiblen und standardisierten, langfristig nutzbaren Formaten f{\"u}r die Forschung erkennen, k{\"o}nnen sie sich mit dem erforderlichen Nachdruck f{\"u}r deren Verbreitung einsetzen und durch die zunehmende Verf{\"u}gbarkeit von Texten in solchen Formaten f{\"u}r die eigene Forschung und Lehre davon profitieren.},
  language  = {de}
}
@phdthesis{Schoenherr2009,
  author    = {Sch{\"o}nherr, Monika},
  title     = {Modalit{\"a}t und Modalit{\"a}tsausdr{\"u}cke in althochdeutschen Bibeltexten. Eine korpusgest{\"u}tzte Analyse},
  isbn      = {978-3-923959-62-4},
  doi       = {10.25972/OPUS-3874},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-46904},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2009},
  abstract  = {Die vorliegende Abhandlung leistet einen Beitrag zu der noch l{\"a}ngst nicht gen{\"u}gend untersuchten Modalit{\"a}tsproblematik in althochdeutschen Bibeltexten. Bei den bisherigen historischen Untersuchungen wurden die kommunikativen Bedingungen f{\"u}r das Vorkommen der Modalit{\"a}tsausdr{\"u}cke nicht oder nicht hinreichend genug beachtet. Daher hat sich die Arbeit zum Ziel gesetzt, die sprachlichen Ausdrucksformen der Modalit{\"a}t unter dem kommunikativen Gesichtspunkt zu behandeln und neue Punkte zum Thema "Modalit{\"a}t im Althochdeutschen" zur Diskussion zu stellen. Die Analyse ist diskursiv angelegt: Die jeweiligen Modalit{\"a}tsformen werden auf dem Hintergrund des gesamten Textes dargestellt und aus dem jeweiligen Kontext heraus erkl{\"a}rt. Als Textgrundlage fungiert das selbst erstellte historische Korpus der zwei biblischen Evangelienharmonien aus dem 9. Jahrhundert (der ahd. 'Tatian' und 'Otfrids Evangelienbuch').},
  subject      = {Modalit{\"a}t <Linguistik>},
  language  = {de}
}
@phdthesis{Binder2005,
  author    = {Binder, Kristina},
  title     = {Das Starinterview : eine vergleichende Textanalyse von Presse-, H{\"o}rfunk-, Fernseh- und Chatinterview},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-13255},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2005},
  abstract  = {No abstract available},
  subject      = {Interview},
  language  = {de}
}
@phdthesis{Beckmann2004,
  author    = {Beckmann, Pia},
  title     = {Schwangerschaftsabbruch als sprachliches Problem : eine linguistische Textanalyse ausgew{\"a}hlter Gesetzentw{\"u}rfe zur Reform des \S 218 StGB},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-9989},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2004},
  abstract  = {Die Arbeit stellt eine linguistische Textanalyse von Gesetzentw{\"u}rfen zur Reform des \S 218 StGB aus dem Jahr 1991 dar. Mitspieler (Aktanten) in den jeweiligen Handlungsframes der Gesetzentw{\"u}rfe sind die Frau als Entscheidungstr{\"a}gerin f{\"u}r die Handlung "Schwangerschaftsabbruch", der Arzt, der den Schwangerschaftsabbruch vornimmt, und der Embryo, der abgetrieben wird. Unter R{\"u}ckgriff auf die Prototypensemantik werden die Handlung und die Aktanten in dem jeweiligen Textzusammenhang der einzelnen Gesetzentw{\"u}rfe analysiert (inclusive einer Frequenzanalyse). Die anschließende Argumentationsanalyse folgt dem Erkl{\"a}rungsmodell von Toulmin zu alltagssprachlichen Argumentationen unter Ber{\"u}cksichtigung der Argumentationsmuster von Kienpointner.},
  subject      = {Deutsch},
  language  = {de}
}