@phdthesis{Ajjour,
  author    = {Ajjour, Yamen},
  title     = {Addressing Controversial Topics in Search Engines},
  doi       = {10.25643/bauhaus-universitaet.6403},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20230626-64037},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {133},
  abstract  = {Search engines are very good at answering queries that look for facts. Still, information needs that concern forming opinions on a controversial topic or making a decision remain a challenge for search engines. Since they are optimized to retrieve satisfying answers, search engines might emphasize a specific stance on a controversial topic in their ranking, amplifying bias in society in an undesired way. Argument retrieval systems support users in forming opinions about controversial topics by retrieving arguments for a given query. In this thesis, we address challenges in argument retrieval systems that concern integrating them in search engines, developing generalizable argument mining approaches, and enabling frame-guided delivery of arguments. Adapting argument retrieval systems to search engines should start by identifying and analyzing information needs that look for arguments. To identify questions that look for arguments we develop a two-step annotation scheme that first identifies whether the context of a question is controversial, and if so, assigns it one of several question types: factual, method, and argumentative. Using this annotation scheme, we create a question dataset from the logs of a major search engine and use it to analyze the characteristics of argumentative questions. The analysis shows that the proportion of argumentative questions on controversial topics is substantial and that they mainly ask for reasons and predictions. The dataset is further used to develop a classifier to uniquely map questions to the question types, reaching a convincing F1-score of 0.78. While the web offers an invaluable source of argumentative content to respond to argumentative questions, it is characterized by multiple genres (e.g., news articles and social fora). Exploiting the web as a source of arguments relies on developing argument mining approaches that generalize over genre. To this end, we approach the problem of how to extract argument units in a genre-robust way. Our experiments on argument unit segmentation show that transfer across genres is rather hard to achieve using existing sequence-to-sequence models. Another property of text which argument mining approaches should generalize over is topic. Since new topics appear daily on which argument mining approaches are not trained, argument mining approaches should be developed in a topic-generalizable way. Towards this goal, we analyze the coverage of 31 argument corpora across topics using three topic ontologies. The analysis shows that the topics covered by existing argument corpora are biased toward a small subset of easily accessible controversial topics, hinting at the inability of existing approaches to generalize across topics. In addition to corpus construction standards, fostering topic generalizability requires a careful formulation of argument mining tasks. Same side stance classification is a reformulation of stance classification that makes it less dependent on the topic. First experiments on this task show promising results in generalizing across topics. To be effective at persuading their audience, users of an argument retrieval system should select arguments from the retrieved results based on what frame they emphasize of a controversial topic. An open challenge is to develop an approach to identify the frames of an argument. To this end, we define a frame as a subset of arguments that share an aspect. We operationalize this model via an approach that identifies and removes the topic of arguments before clustering them into frames. We evaluate the approach on a dataset that covers 12,326 frames and show that identifying the topic of an argument and removing it helps to identify its frames.},
  subject      = {Informatik},
  language  = {en}
}
@phdthesis{Kiesel2022,
  author    = {Kiesel, Johannes},
  title     = {Harnessing Web Archives to Tackle Selected Societal Challenges},
  doi       = {10.25643/bauhaus-universitaet.4660},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220622-46602},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  year      = {2022},
  abstract  = {With the growing importance of the World Wide Web, the major challenges our society faces are also increasingly affecting the digital areas of our lives. Some of the associated problems can be addressed by computer science, and some of these specifically by data-driven research. To do so, however, requires to solve open issues related to archive quality and the large volume and variety of the data contained. This dissertation contributes data, algorithms, and concepts towards leveraging the big data and temporal provenance capabilities of web archives to tackle societal challenges. We selected three such challenges that highlight the central issues of archive quality, data volume, and data variety, respectively: (1) For the preservation of digital culture, this thesis investigates and improves the automatic quality assurance of the web page archiving process, as well as the further processing of the resulting archive data for automatic analysis. (2) For the critical assessment of information, this thesis examines large datasets of Wikipedia and news articles and presents new methods for automatically determining quality and bias. (3) For digital security and privacy, this thesis exploits the variety of content on the web to quantify the security of mnemonic passwords and analyzes the privacy-aware re-finding of the various seen content through private web archives.},
  subject      = {Informatik},
  language  = {en}
}
@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{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}
}
@phdthesis{Bunte,
  author    = {Bunte, Andreas},
  title     = {Entwicklung einer ontologiebasierten Beschreibung zur Erh{\"o}hung des Automatisierungsgrades in der Produktion},
  doi       = {10.25643/bauhaus-universitaet.4315},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20201215-43156},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {189},
  abstract  = {Die zu beobachtenden k{\"u}rzeren Produktlebenszyklen und eine schnellere Marktdurchdringung von Produkttechnologien erfordern adaptive und leistungsf{\"a}hige Produktionsanlagen. Die Adaptivit{\"a}t erm{\"o}glicht eine Anpassung der Produktionsanlage an neue Produkte, und die Leistungsf{\"a}higkeit der Anlage stellt sicher, dass ausreichend Produkte in kurzer Zeit und zu geringen Kosten hergestellt werden k{\"o}nnen. Durch eine Modularisierung der Produktionsanlage kann die Adaptivit{\"a}t erreicht werden. Jedoch erfordert heutzutage jede Adaption manuellen Aufwand, z.B. zur Anpassung von propriet{\"a}ren Signalen oder zur Anpassung {\"u}bergeordneter Funktionen. Dadurch sinkt die Leistungsf{\"a}higkeit der Anlage. Das Ziel dieser Arbeit ist es, die Interoperabilit{\"a}t in Bezug auf die Informationsverwendung in modularen Produktionsanlagen zu gew{\"a}hrleisten. Dazu werden Informationen durch semantische Modelle beschrieben. Damit wird ein einheitlicher Informationszugriff erm{\"o}glicht, und {\"u}bergeordnete Funktionen erhalten Zugriff auf alle Informationen der Produktionsmodule, unabh{\"a}ngig von dem Typ, dem Hersteller und dem Alter des Moduls. Dadurch entf{\"a}llt der manuelle Aufwand bei Anpassungen des modularen Produktionssystems, wodurch die Leistungsf{\"a}higkeit der Anlage gesteigert und Stillstandszeiten reduziert werden. Nach dem Ermitteln der Anforderungen an einen Modellierungsformalismus wurden potentielle Formalismen mit den Anforderungen abgeglichen. OWL DL stellte sich als geeigneter Formalismus heraus und wurde f{\"u}r die Erstellung des semantischen Modells in dieser Arbeit verwendet. Es wurde exemplarisch ein semantisches Modell f{\"u}r die drei Anwendungsf{\"a}lle Interaktion, Orchestrierung und Diagnose erstellt. Durch einen Vergleich der Modellierungselemente von unterschiedlichen Anwendungsf{\"a}llen wurde die Allgemeing{\"u}ltigkeit des Modells bewertet. Dabei wurde gezeigt, dass die Erreichung eines allgemeinen Modells f{\"u}r technische Anwendungsf{\"a}lle m{\"o}glich ist und lediglich einige Hundert Begriffe ben{\"o}tigt. Zur Evaluierung der erstellten Modelle wurde ein wandlungsf{\"a}higes Produktionssystem der SmartFactoryOWL verwendet, an dem die Anwendungsf{\"a}lle umgesetzt wurden. Dazu wurde eine Laufzeitumgebung erstellt, die die semantischen Modelle der einzelnen Module zu einem Gesamtmodell vereint, Daten aus der Anlage in das Modell {\"u}bertr{\"a}gt und eine Schnittstelle f{\"u}r die Services bereitstellt. Die Services realisieren {\"u}bergeordnete Funktionen und verwenden die Informationen des semantischen Modells. In allen drei Anwendungsf{\"a}llen wurden die semantischen Modelle korrekt zusammengef{\"u}gt und mit den darin enthaltenen Informationen konnte die Aufgabe des jeweiligen Anwendungsfalles ohne zus{\"a}tzlichen manuellen Aufwand gel{\"o}st werden.},
  subject      = {Ontologie},
  language  = {de}
}
@phdthesis{Voelske,
  author    = {V{\"o}lske, Michael},
  title     = {Retrieval Enhancements for Task-Based Web Search},
  doi       = {10.25643/bauhaus-universitaet.3942},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20190709-39422},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  abstract  = {The task-based view of web search implies that retrieval should take the user perspective into account. Going beyond merely retrieving the most relevant result set for the current query, the retrieval system should aim to surface results that are actually useful to the task that motivated the query. This dissertation explores how retrieval systems can better understand and support their users' tasks from three main angles: First, we study and quantify search engine user behavior during complex writing tasks, and how task success and behavior are associated in such settings. Second, we investigate search engine queries formulated as questions, and explore patterns in a large query log that may help search engines to better support this increasingly prevalent interaction pattern. Third, we propose a novel approach to reranking the search result lists produced by web search engines, taking into account retrieval axioms that formally specify properties of a good ranking.},
  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{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{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}
}