@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}
}
@misc{Reger2016,
  type      = {Master Thesis},
  author    = {Reger, Isabella},
  title     = {Figurennetzwerke als {\"A}hnlichkeitsmaß},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-149106},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2016},
  abstract  = {Die vorliegende Arbeit l{\"a}sst sich dem Bereich der quantitativen Literaturanalyse zuordnen und verfolgt das Ziel, mittels computergest{\"u}tzter Verfahren zu untersuchen, inwieweit sich Romane hinsichtlich ihrer Figurenkonstellation {\"a}hneln. Dazu wird die Figurenkonstellation, als wichtiges strukturgebendes Ordnungsprinzip eines Romans, als soziales Netzwerk der Figuren operationalisiert. Solche Netzwerke k{\"o}nnen unter Anwendung von Verfahren des Natural Language Processing automatisch aus dem Text erstellt werden. Als Datengrundlage dient ein Korpus von deutschsprachigen Romanen aus dem 19. Jahrhundert, das mit automatischen Verfahren zur Figurenerkennung und Koreferenzaufl{\"o}sung prozessiert und manuell nachkorrigiert wurde, um eine m{\"o}glichst saubere Datenbasis zu schaffen. Ausgehend von der intensiven vergleichenden Betrachtung der Figurenkonstellationen von Fontanes "Effi Briest" und Flauberts "Madame Bovary" wurde in einer manuell erstellten Distanzmatrix die menschliche Intuition solcher {\"A}hnlichkeit zwischen allen Romanen des Korpus festgehalten, basierend auf der Lekt{\"u}re von Zusammenfassungen der Romane. Diese Daten werden als Evaluationsgrundlage genutzt. Mit Hilfe von Methoden der sozialen Netzwerkanalyse k{\"o}nnen strukturelle Eigenschaften dieser Netzwerke als Features erhoben werden. Diese wurden anschließend zur Berechnung der Kosinusdistanz zwischen den Romanen verwendet. Obwohl die automatisch erstellten Netzwerke die Figurenkonstellationen der Romane im Allgemeinen gut widerspiegeln und die Netzwerkfeatures sinnvoll interpretierbar sind, war die Korrelation mit der Evaluationsgrundlage niedrig. Dies legt die Vermutung nahe, dass neben der Struktur der Figurenkonstellation auch wiederkehrende Themen und Motive die Erstellung der Evaluationsgrundlage unterbewusst beeinflusst haben. Daher wurde Topic Modeling angewendet, um wichtige zwischenmenschliche Motive zu modellieren, die f{\"u}r die Figurenkonstellation von Bedeutung sein k{\"o}nnen. Die Netzwerkfeatures und die Topic-Verteilung wurden in Kombination zur Distanzberechnung herangezogen. Außerdem wurde versucht, jeder Kante des Figurennetzwerks ein Topic zuzuordnen, das diese Kante inhaltlich beschreibt. Hier zeigte sich, dass einerseits Topics, die sehr spezifisch f{\"u}r bestimmte Texte sind, und andererseits Topics, die {\"u}ber alle Texte hinweg stark vertreten sind, das Ergebnis bestimmen, sodass wiederum keine, bzw. nur eine sehr schwache Korrelation mit der Evaluationsgrundlage gefunden werden konnte. Der Umstand, dass keine Verbindung zwischen den berechneten Distanzen und der Evaluationsgrundlage gefunden werden konnte, obwohl die einzelnen Features sinnvoll interpretierbar sind, l{\"a}sst Zweifel an der Evaluationsmatrix aufkommen. Diese scheint st{\"a}rker als zu Beginn angenommen unterbewusst von thematischen und motivischen {\"A}hnlichkeiten zwischen den Romanen beeinflusst zu sein. Auch die Qualit{\"a}t der jeweiligen Zusammenfassung hat hier einen nicht unwesentlichen Einfluss. Daher w{\"a}re eine weniger subjektiv gepr{\"a}gte M{\"o}glichkeit der Auswertung von N{\"o}ten, beispielsweise durch die parallele Einsch{\"a}tzung mehrerer Annotatoren. Auch die weitere Verbesserung von NLP-Verfahren f{\"u}r literarische Texte in deutscher Sprache ist ein Desideratum f{\"u}r ankn{\"u}pfende Forschungsans{\"a}tze.},
  subject      = {Digital Humanities},
  language  = {de}
}