@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{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}
}