@phdthesis{Gollub,
  author    = {Gollub, Tim},
  title     = {Information Retrieval for the Digital Humanities},
  doi       = {10.25643/bauhaus-universitaet.4673},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220801-46738},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {177},
  abstract  = {In ten chapters, this thesis presents information retrieval technology which is tailored to the research activities that arise in the context of corpus-based digital humanities projects. The presentation is structured by a conceptual research process that is introduced in Chapter 1. The process distinguishes a set of five research activities: research question generation, corpus acquisition, research question modeling, corpus annotation, and result dissemination. Each of these research activities elicits different information retrieval tasks with special challenges, for which algorithmic approaches are presented after an introduction of the core information retrieval concepts in Chapter 2. A vital concept in many of the presented approaches is the keyquery paradigm introduced in Chapter 3, which represents an operation that returns relevant search queries in response to a given set of input documents. Keyqueries are proposed in Chapter 4 for the recommendation of related work, and in Chapter 5 for improving access to aspects hidden in the long tail of search result lists. With pseudo-descriptions, a document expansion approach is presented in Chapter 6. The approach improves the retrieval performance for corpora where only bibliographic meta-data is originally available. In Chapter 7, the keyquery paradigm is employed to generate dynamic taxonomies for corpora in an unsupervised fashion. Chapter 8 turns to the exploration of annotated corpora, and presents scoped facets as a conceptual extension to faceted search systems, which is particularly useful in exploratory search settings. For the purpose of highlighting the major topical differences in a sequence of sub-corpora, an algorithm called topical sequence profiling is presented in Chapter 9. The thesis concludes with two pilot studies regarding the visualization of (re)search results for the means of successful result dissemination: a metaphoric interpretation of the information nutrition label, as well as the philosophical bodies, which are 3D-printed search results.},
  subject      = {Information Retrieval},
  language  = {en}
}
@phdthesis{Anderka,
  author    = {Anderka, Maik},
  title     = {Analyzing and Predicting Quality Flaws in User-generated Content: The Case of Wikipedia},
  doi       = {10.25643/bauhaus-universitaet.1977},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20130709-19778},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  abstract  = {Web applications that are based on user-generated content are often criticized for containing low-quality information; a popular example is the online encyclopedia Wikipedia. The major points of criticism pertain to the accuracy, neutrality, and reliability of information. The identification of low-quality information is an important task since for a huge number of people around the world it has become a habit to first visit Wikipedia in case of an information need. Existing research on quality assessment in Wikipedia either investigates only small samples of articles, or else deals with the classification of content into high-quality or low-quality. This thesis goes further, it targets the investigation of quality flaws, thus providing specific indications of the respects in which low-quality content needs improvement. The original contributions of this thesis, which relate to the fields of user-generated content analysis, data mining, and machine learning, can be summarized as follows: (1) We propose the investigation of quality flaws in Wikipedia based on user-defined cleanup tags. Cleanup tags are commonly used in the Wikipedia community to tag content that has some shortcomings. Our approach is based on the hypothesis that each cleanup tag defines a particular quality flaw. (2) We provide the first comprehensive breakdown of Wikipedia's quality flaw structure. We present a flaw organization schema, and we conduct an extensive exploratory data analysis which reveals (a) the flaws that actually exist, (b) the distribution of flaws in Wikipedia, and, (c) the extent of flawed content. (3) We present the first breakdown of Wikipedia's quality flaw evolution. We consider the entire history of the English Wikipedia from 2001 to 2012, which comprises more than 508 million page revisions, summing up to 7.9 TB. Our analysis reveals (a) how the incidence and the extent of flaws have evolved, and, (b) how the handling and the perception of flaws have changed over time. (4) We are the first who operationalize an algorithmic prediction of quality flaws in Wikipedia. We cast quality flaw prediction as a one-class classification problem, develop a tailored quality flaw model, and employ a dedicated one-class machine learning approach. A comprehensive evaluation based on human-labeled Wikipedia articles underlines the practical applicability of our approach.},
  subject      = {Data Mining},
  language  = {en}
}
@phdthesis{Potthast,
  author    = {Potthast, Martin},
  title     = {Technologies for Reusing Text from the Web},
  doi       = {10.25643/bauhaus-universitaet.1566},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20120217-15663},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {237},
  abstract  = {Texts from the web can be reused individually or in large quantities. The former is called text reuse and the latter language reuse. We first present a comprehensive overview of the different ways in which text and language is reused today, and how exactly information retrieval technologies can be applied in this respect. The remainder of the thesis then deals with specific retrieval tasks. In general, our contributions consist of models and algorithms, their evaluation, and for that purpose, large-scale corpus construction. The thesis divides into two parts. The first part introduces technologies for text reuse detection, and our contributions are as follows: (1) A unified view of projecting-based and embedding-based fingerprinting for near-duplicate detection and the first time evaluation of fingerprint algorithms on Wikipedia revision histories as a new, large-scale corpus of near-duplicates. (2) A new retrieval model for the quantification of cross-language text similarity, which gets by without parallel corpora. We have evaluated the model in comparison to other models on many different pairs of languages. (3) An evaluation framework for text reuse and particularly plagiarism detectors, which consists of tailored detection performance measures and a large-scale corpus of automatically generated and manually written plagiarism cases. The latter have been obtained via crowdsourcing. This framework has been successfully applied to evaluate many different state-of-the-art plagiarism detection approaches within three international evaluation competitions. The second part introduces technologies that solve three retrieval tasks based on language reuse, and our contributions are as follows: (4) A new model for the comparison of textual and non-textual web items across media, which exploits web comments as a source of information about the topic of an item. In this connection, we identify web comments as a largely neglected information source and introduce the rationale of comment retrieval. (5) Two new algorithms for query segmentation, which exploit web n-grams and Wikipedia as a means of discerning the user intent of a keyword query. Moreover, we crowdsource a new corpus for the evaluation of query segmentation which surpasses existing corpora by two orders of magnitude. (6) A new writing assistance tool called Netspeak, which is a search engine for commonly used language. Netspeak indexes the web in the form of web n-grams as a source of writing examples and implements a wildcard query processor on top of it.},
  subject      = {Information Retrieval},
  language  = {en}
}
@phdthesis{Lipka,
  author    = {Lipka, Nedim},
  title     = {Modeling Non-Standard Text Classification Tasks},
  doi       = {10.25643/bauhaus-universitaet.1862},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20130307-18626},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  abstract  = {Text classification deals with discovering knowledge in texts and is used for extracting, filtering, or retrieving information in streams and collections. The discovery of knowledge is operationalized by modeling text classification tasks, which is mainly a human-driven engineering process. The outcome of this process, a text classification model, is used to inductively learn a text classification solution from a priori classified examples. The building blocks of modeling text classification tasks cover four aspects: (1) the way examples are represented, (2) the way examples are selected, (3) the way classifiers learn from examples, and (4) the way models are selected. This thesis proposes methods that improve the prediction quality of text classification solutions for unseen examples, especially for non-standard tasks where standard models do not fit. The original contributions are related to the aforementioned building blocks: (1) Several topic-orthogonal text representations are studied in the context of non-standard tasks and a new representation, namely co-stems, is introduced. (2) A new active learning strategy that goes beyond standard sampling is examined. (3) A new one-class ensemble for improving the effectiveness of one-class classification is proposed. (4) A new model selection framework to cope with subclass distribution shifts that occur in dynamic environments is introduced.},
  subject      = {Text Classification},
  language  = {en}
}
@phdthesis{AlKhatib2021,
  author    = {Al Khatib, Khalid},
  title     = {Computational Analysis of Argumentation Strategies},
  doi       = {10.25643/bauhaus-universitaet.4461},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210719-44612},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {134},
  year      = {2021},
  abstract  = {The computational analysis of argumentation strategies is substantial for many downstream applications. It is required for nearly all kinds of text synthesis, writing assistance, and dialogue-management tools. While various tasks have been tackled in the area of computational argumentation, such as argumentation mining and quality assessment, the task of the computational analysis of argumentation strategies in texts has so far been overlooked. This thesis principally approaches the analysis of the strategies manifested in the persuasive argumentative discourses that aim for persuasion as well as in the deliberative argumentative discourses that aim for consensus. To this end, the thesis presents a novel view of argumentation strategies for the above two goals. Based on this view, new models for pragmatic and stylistic argument attributes are proposed, new methods for the identification of the modelled attributes have been developed, and a new set of strategy principles in texts according to the identified attributes is presented and explored. Overall, the thesis contributes to the theory, data, method, and evaluation aspects of the analysis of argumentation strategies. The models, methods, and principles developed and explored in this thesis can be regarded as essential for promoting the applications mentioned above, among others.},
  subject      = {Argumentation},
  language  = {en}
}
@masterthesis{Lang,
  type      = {Bachelor Thesis},
  author    = {Lang, Kevin},
  title     = {Worteinbettung als semantisches Feature in der argumentativen Analyse},
  doi       = {10.25643/bauhaus-universitaet.3934},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20190617-39343},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {54},
  abstract  = {Diese Arbeit besch{\"a}ftigt sich mit der Nutzung von Worteinbettungen in der automatischen Analyse von argumentativen Texten. Die Arbeit diskutiert wichtige Einstellungen des Einbettungsverfahren sowie diverse Anwendungsmethoden der eingebetteten Wortvektoren f{\"u}r drei Aufgaben der automatischen argumentativen Analyse: Textsegmentierung, Argumentativit{\"a}ts-Klassifikation und Relationenfindung. Meine Experimente auf zwei Standard-Argumentationsdatens{\"a}tzen zeigen die folgenden Haupterkenntnisse: Bei der Textsegmentierung konnten keine Verbesserungen erzielt werden, w{\"a}hrend in der Argumentativit{\"a}ts-Klassifikation und der Relationenfindung sich kleine Erfolge gezeigt haben und weitere bestimmte Forschungsthesen bewahrheitet werden konnten. In der Diskussion wird darauf eingegangen, warum bei der einfachen Worteinbettung in der argumentativen Analyse sich kaum nutzbare Ergebnisse erzielen lassen konnten, diese sich aber in Zukunft durch erweiterte Worteinbettungsverfahren verbessern k{\"o}nnen.},
  subject      = {Argumentation},
  language  = {de}
}
@misc{Lang,
  type      = {Master Thesis},
  author    = {Lang, Kevin},
  title     = {Argument Search with Voice Assistants},
  doi       = {10.25643/bauhaus-universitaet.3935},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20190617-39353},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {100},
  abstract  = {The need for finding persuasive arguments can arise in a variety of domains such as politics, finance, marketing or personal entertainment. In these domains, there is a demand to make decisions by oneself or to convince somebody about a specific topic. To obtain a conclusion, one has to search thoroughly different sources in literature and on the web to compare various arguments. Voice interfaces, in form of smartphone applications or smart speakers, present the user with natural conversations in a comfortable way to make search requests in contrast to a traditional search interface with keyboard and display. Benefits and obstacles of such a new interface are analyzed by conducting two studies. The first one consists of a survey for analyzing the target group with questions about situations, motivations, and possible demanding features. The latter one is a wizard-of-oz experiment to investigate possible queries on how a user formulates requests to such a novel system. The results indicate that a search interface with conversational abilities can build a helpful assistant, but to satisfy the demands of a broader audience some additional information retrieval and visualization features need to be implemented.},
  subject      = {Amazon Alexa},
  language  = {en}
}