@phdthesis{Harmouch2020,
  author    = {Harmouch, Hazar},
  title     = {Single-column data profiling},
  doi       = {10.25932/publishup-47455},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-474554},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 115},
  year      = {2020},
  abstract  = {The research area of data profiling consists of a large set of methods and processes to examine a given dataset and determine metadata about it. Typically, different data profiling tasks address different kinds of metadata, comprising either various statistics about individual columns (Single-column Analysis) or relationships among them (Dependency Discovery). Among the basic statistics about a column are data type, header, the number of unique values (the column's cardinality), maximum and minimum values, the number of null values, and the value distribution. Dependencies involve, for instance, functional dependencies (FDs), inclusion dependencies (INDs), and their approximate versions. Data profiling has a wide range of conventional use cases, namely data exploration, cleansing, and integration. The produced metadata is also useful for database management and schema reverse engineering. Data profiling has also more novel use cases, such as big data analytics. The generated metadata describes the structure of the data at hand, how to import it, what it is about, and how much of it there is. Thus, data profiling can be considered as an important preparatory task for many data analysis and mining scenarios to assess which data might be useful and to reveal and understand a new dataset's characteristics. In this thesis, the main focus is on the single-column analysis class of data profiling tasks. We study the impact and the extraction of three of the most important metadata about a column, namely the cardinality, the header, and the number of null values. First, we present a detailed experimental study of twelve cardinality estimation algorithms. We classify the algorithms and analyze their efficiency, scaling far beyond the original experiments and testing theoretical guarantees. Our results highlight their trade-offs and point out the possibility to create a parallel or a distributed version of these algorithms to cope with the growing size of modern datasets. Then, we present a fully automated, multi-phase system to discover human-understandable, representative, and consistent headers for a target table in cases where headers are missing, meaningless, or unrepresentative for the column values. Our evaluation on Wikipedia tables shows that 60\% of the automatically discovered schemata are exact and complete. Considering more schema candidates, top-5 for example, increases this percentage to 72\%. Finally, we formally and experimentally show the ghost and fake FDs phenomenon caused by FD discovery over datasets with missing values. We propose two efficient scores, probabilistic and likelihood-based, for estimating the genuineness of a discovered FD. Our extensive set of experiments on real-world and semi-synthetic datasets show the effectiveness and efficiency of these scores.},
  language  = {en}
}
@phdthesis{Koumarelas2020,
  author    = {Koumarelas, Ioannis},
  title     = {Data preparation and domain-agnostic duplicate detection},
  doi       = {10.25932/publishup-48913},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489131},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 97},
  year      = {2020},
  abstract  = {Successfully completing any data science project demands careful consideration across its whole process. Although the focus is often put on later phases of the process, in practice, experts spend more time in earlier phases, preparing data, to make them consistent with the systems' requirements or to improve their models' accuracies. Duplicate detection is typically applied during the data cleaning phase, which is dedicated to removing data inconsistencies and improving the overall quality and usability of data. While data cleaning involves a plethora of approaches to perform specific operations, such as schema alignment and data normalization, the task of detecting and removing duplicate records is particularly challenging. Duplicates arise when multiple records representing the same entities exist in a database. Due to numerous reasons, spanning from simple typographical errors to different schemas and formats of integrated databases. Keeping a database free of duplicates is crucial for most use-cases, as their existence causes false negatives and false positives when matching queries against it. These two data quality issues have negative implications for tasks, such as hotel booking, where users may erroneously select a wrong hotel, or parcel delivery, where a parcel can get delivered to the wrong address. Identifying the variety of possible data issues to eliminate duplicates demands sophisticated approaches. While research in duplicate detection is well-established and covers different aspects of both efficiency and effectiveness, our work in this thesis focuses on the latter. We propose novel approaches to improve data quality before duplicate detection takes place and apply the latter in datasets even when prior labeling is not available. Our experiments show that improving data quality upfront can increase duplicate classification results by up to 19\%. To this end, we propose two novel pipelines that select and apply generic as well as address-specific data preparation steps with the purpose of maximizing the success of duplicate detection. Generic data preparation, such as the removal of special characters, can be applied to any relation with alphanumeric attributes. When applied, data preparation steps are selected only for attributes where there are positive effects on pair similarities, which indirectly affect classification, or on classification directly. Our work on addresses is twofold; first, we consider more domain-specific approaches to improve the quality of values, and, second, we experiment with known and modified versions of similarity measures to select the most appropriate per address attribute, e.g., city or country. To facilitate duplicate detection in applications where gold standard annotations are not available and obtaining them is not possible or too expensive, we propose MDedup. MDedup is a novel, rule-based, and fully automatic duplicate detection approach that is based on matching dependencies. These dependencies can be used to detect duplicates and can be discovered using state-of-the-art algorithms efficiently and without any prior labeling. MDedup uses two pipelines to first train on datasets with known labels, learning to identify useful matching dependencies, and then be applied on unseen datasets, regardless of any existing gold standard. Finally, our work is accompanied by open source code to enable repeatability of our research results and application of our approaches to other datasets.},
  language  = {en}
}
@phdthesis{Lazaridou2021,
  author    = {Lazaridou, Konstantina},
  title     = {Revealing hidden patterns in political news and social media with machine learning},
  doi       = {10.25932/publishup-50273},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-502734},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xv, 140},
  year      = {2021},
  abstract  = {As part of our everyday life we consume breaking news and interpret it based on our own viewpoints and beliefs. We have easy access to online social networking platforms and news media websites, where we inform ourselves about current affairs and often post about our own views, such as in news comments or social media posts. The media ecosystem enables opinions and facts to travel from news sources to news readers, from news article commenters to other readers, from social network users to their followers, etc. The views of the world many of us have depend on the information we receive via online news and social media. Hence, it is essential to maintain accurate, reliable and objective online content to ensure democracy and verity on the Web. To this end, we contribute to a trustworthy media ecosystem by analyzing news and social media in the context of politics to ensure that media serves the public interest. In this thesis, we use text mining, natural language processing and machine learning techniques to reveal underlying patterns in political news articles and political discourse in social networks. Mainstream news sources typically cover a great amount of the same news stories every day, but they often place them in a different context or report them from different perspectives. In this thesis, we are interested in how distinct and predictable newspaper journalists are, in the way they report the news, as a means to understand and identify their different political beliefs. To this end, we propose two models that classify text from news articles to their respective original news source, i.e., reported speech and also news comments. Our goal is to capture systematic quoting and commenting patterns by journalists and news commenters respectively, which can lead us to the newspaper where the quotes and comments are originally published. Predicting news sources can help us understand the potential subjective nature behind news storytelling and the magnitude of this phenomenon. Revealing this hidden knowledge can restore our trust in media by advancing transparency and diversity in the news. Media bias can be expressed in various subtle ways in the text and it is often challenging to identify these bias manifestations correctly, even for humans. However, media experts, e.g., journalists, are a powerful resource that can help us overcome the vague definition of political media bias and they can also assist automatic learners to find the hidden bias in the text. Due to the enormous technological advances in artificial intelligence, we hypothesize that identifying political bias in the news could be achieved through the combination of sophisticated deep learning modelsxi and domain expertise. Therefore, our second contribution is a high-quality and reliable news dataset annotated by journalists for political bias and a state-of-the-art solution for this task based on curriculum learning. Our aim is to discover whether domain expertise is necessary for this task and to provide an automatic solution for this traditionally manually-solved problem. User generated content is fundamentally different from news articles, e.g., messages are shorter, they are often personal and opinionated, they refer to specific topics and persons, etc. Regarding political and socio-economic news, individuals in online communities make use of social networks to keep their peers up-to-date and to share their own views on ongoing affairs. We believe that social media is also an as powerful instrument for information flow as the news sources are, and we use its unique characteristic of rapid news coverage for two applications. We analyze Twitter messages and debate transcripts during live political presidential debates to automatically predict the topics that Twitter users discuss. Our goal is to discover the favoured topics in online communities on the dates of political events as a way to understand the political subjects of public interest. With the up-to-dateness of microblogs, an additional opportunity emerges, namely to use social media posts and leverage the real-time verity about discussed individuals to find their locations. That is, given a person of interest that is mentioned in online discussions, we use the wisdom of the crowd to automatically track her physical locations over time. We evaluate our approach in the context of politics, i.e., we predict the locations of US politicians as a proof of concept for important use cases, such as to track people that are national risks, e.g., warlords and wanted criminals.},
  language  = {en}
}
@phdthesis{Loster2021,
  author    = {Loster, Michael},
  title     = {Knowledge base construction with machine learning methods},
  doi       = {10.25932/publishup-50145},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-501459},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 130},
  year      = {2021},
  abstract  = {Modern knowledge bases contain and organize knowledge from many different topic areas. Apart from specific entity information, they also store information about their relationships amongst each other. Combining this information results in a knowledge graph that can be particularly helpful in cases where relationships are of central importance. Among other applications, modern risk assessment in the financial sector can benefit from the inherent network structure of such knowledge graphs by assessing the consequences and risks of certain events, such as corporate insolvencies or fraudulent behavior, based on the underlying network structure. As public knowledge bases often do not contain the necessary information for the analysis of such scenarios, the need arises to create and maintain dedicated domain-specific knowledge bases. This thesis investigates the process of creating domain-specific knowledge bases from structured and unstructured data sources. In particular, it addresses the topics of named entity recognition (NER), duplicate detection, and knowledge validation, which represent essential steps in the construction of knowledge bases. As such, we present a novel method for duplicate detection based on a Siamese neural network that is able to learn a dataset-specific similarity measure which is used to identify duplicates. Using the specialized network architecture, we design and implement a knowledge transfer between two deduplication networks, which leads to significant performance improvements and a reduction of required training data. Furthermore, we propose a named entity recognition approach that is able to identify company names by integrating external knowledge in the form of dictionaries into the training process of a conditional random field classifier. In this context, we study the effects of different dictionaries on the performance of the NER classifier. We show that both the inclusion of domain knowledge as well as the generation and use of alias names results in significant performance improvements. For the validation of knowledge represented in a knowledge base, we introduce Colt, a framework for knowledge validation based on the interactive quality assessment of logical rules. In its most expressive implementation, we combine Gaussian processes with neural networks to create Colt-GP, an interactive algorithm for learning rule models. Unlike other approaches, Colt-GP uses knowledge graph embeddings and user feedback to cope with data quality issues of knowledge bases. The learned rule model can be used to conditionally apply a rule and assess its quality. Finally, we present CurEx, a prototypical system for building domain-specific knowledge bases from structured and unstructured data sources. Its modular design is based on scalable technologies, which, in addition to processing large datasets, ensures that the modules can be easily exchanged or extended. CurEx offers multiple user interfaces, each tailored to the individual needs of a specific user group and is fully compatible with the Colt framework, which can be used as part of the system. We conduct a wide range of experiments with different datasets to determine the strengths and weaknesses of the proposed methods. To ensure the validity of our results, we compare the proposed methods with competing approaches.},
  language  = {en}
}
@phdthesis{Repke2022,
  author    = {Repke, Tim},
  title     = {Machine-learning-assisted corpus exploration and visualisation},
  doi       = {10.25932/publishup-56263},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-562636},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xii, 131},
  year      = {2022},
  abstract  = {Text collections, such as corpora of books, research articles, news, or business documents are an important resource for knowledge discovery. Exploring large document collections by hand is a cumbersome but necessary task to gain new insights and find relevant information. Our digitised society allows us to utilise algorithms to support the information seeking process, for example with the help of retrieval or recommender systems. However, these systems only provide selective views of the data and require some prior knowledge to issue meaningful queries and asses a system's response. The advancements of machine learning allow us to reduce this gap and better assist the information seeking process. For example, instead of sighting countless business documents by hand, journalists and investigator scan employ natural language processing techniques, such as named entity recognition. Al-though this greatly improves the capabilities of a data exploration platform, the wealth of information is still overwhelming. An overview of the entirety of a dataset in the form of a two-dimensional map-like visualisation may help to circumvent this issue. Such overviews enable novel interaction paradigms for users, which are similar to the exploration of digital geographical maps. In particular, they can provide valuable context by indicating how apiece of information fits into the bigger picture.This thesis proposes algorithms that appropriately pre-process heterogeneous documents and compute the layout for datasets of all kinds. Traditionally, given high-dimensional semantic representations of the data, so-called dimensionality reduction algorithms are usedto compute a layout of the data on a two-dimensional canvas. In this thesis, we focus on text corpora and go beyond only projecting the inherent semantic structure itself. Therefore,we propose three dimensionality reduction approaches that incorporate additional information into the layout process: (1) a multi-objective dimensionality reduction algorithm to jointly visualise semantic information with inherent network information derived from the underlying data; (2) a comparison of initialisation strategies for different dimensionality reduction algorithms to generate a series of layouts for corpora that grow and evolve overtime; (3) and an algorithm that updates existing layouts by incorporating user feedback provided by pointwise drag-and-drop edits. This thesis also contains system prototypes to demonstrate the proposed technologies, including pre-processing and layout of the data and presentation in interactive user interfaces.},
  language  = {en}
}
@phdthesis{Draisbach2022,
  author    = {Draisbach, Uwe},
  title     = {Efficient duplicate detection and the impact of transitivity},
  doi       = {10.25932/publishup-57214},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-572140},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, 150},
  year      = {2022},
  abstract  = {Duplicate detection describes the process of finding multiple representations of the same real-world entity in the absence of a unique identifier, and has many application areas, such as customer relationship management, genealogy and social sciences, or online shopping. Due to the increasing amount of data in recent years, the problem has become even more challenging on the one hand, but has led to a renaissance in duplicate detection research on the other hand. This thesis examines the effects and opportunities of transitive relationships on the duplicate detection process. Transitivity implies that if record pairs ⟨ri,rj⟩ and ⟨rj,rk⟩ are classified as duplicates, then also record pair ⟨ri,rk⟩ has to be a duplicate. However, this reasoning might contradict with the pairwise classification, which is usually based on the similarity of objects. An essential property of similarity, in contrast to equivalence, is that similarity is not necessarily transitive. First, we experimentally evaluate the effect of an increasing data volume on the threshold selection to classify whether a record pair is a duplicate or non-duplicate. Our experiments show that independently of the pair selection algorithm and the used similarity measure, selecting a suitable threshold becomes more difficult with an increasing number of records due to an increased probability of adding a false duplicate to an existing cluster. Thus, the best threshold changes with the dataset size, and a good threshold for a small (possibly sampled) dataset is not necessarily a good threshold for a larger (possibly complete) dataset. As data grows over time, earlier selected thresholds are no longer a suitable choice, and the problem becomes worse for datasets with larger clusters. Second, we present with the Duplicate Count Strategy (DCS) and its enhancement DCS++ two alternatives to the standard Sorted Neighborhood Method (SNM) for the selection of candidate record pairs. DCS adapts SNMs window size based on the number of detected duplicates and DCS++ uses transitive dependencies to save complex comparisons for finding duplicates in larger clusters. We prove that with a proper (domain- and data-independent!) threshold, DCS++ is more efficient than SNM without loss of effectiveness. Third, we tackle the problem of contradicting pairwise classifications. Usually, the transitive closure is used for pairwise classifications to obtain a transitively closed result set. However, the transitive closure disregards negative classifications. We present three new and several existing clustering algorithms and experimentally evaluate them on various datasets and under various algorithm configurations. The results show that the commonly used transitive closure is inferior to most other clustering algorithms, especially for the precision of results. In scenarios with larger clusters, our proposed EMCC algorithm is, together with Markov Clustering, the best performing clustering approach for duplicate detection, although its runtime is longer than Markov Clustering due to the subexponential time complexity. EMCC especially outperforms Markov Clustering regarding the precision of the results and additionally has the advantage that it can also be used in scenarios where edge weights are not available.},
  language  = {en}
}
@phdthesis{Jain2022,
  author    = {Jain, Nitisha},
  title     = {Representation and curation of knowledge graphs with embeddings},
  doi       = {10.25932/publishup-61224},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-612240},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 104},
  year      = {2022},
  abstract  = {Knowledge graphs are structured repositories of knowledge that store facts about the general world or a particular domain in terms of entities and their relationships. Owing to the heterogeneity of use cases that are served by them, there arises a need for the automated construction of domain- specific knowledge graphs from texts. While there have been many research efforts towards open information extraction for automated knowledge graph construction, these techniques do not perform well in domain-specific settings. Furthermore, regardless of whether they are constructed automatically from specific texts or based on real-world facts that are constantly evolving, all knowledge graphs inherently suffer from incompleteness as well as errors in the information they hold. This thesis investigates the challenges encountered during knowledge graph construction and proposes techniques for their curation (a.k.a. refinement) including the correction of semantic ambiguities and the completion of missing facts. Firstly, we leverage existing approaches for the automatic construction of a knowledge graph in the art domain with open information extraction techniques and analyse their limitations. In particular, we focus on the challenging task of named entity recognition for artwork titles and show empirical evidence of performance improvement with our proposed solution for the generation of annotated training data. Towards the curation of existing knowledge graphs, we identify the issue of polysemous relations that represent different semantics based on the context. Having concrete semantics for relations is important for downstream appli- cations (e.g. question answering) that are supported by knowledge graphs. Therefore, we define the novel task of finding fine-grained relation semantics in knowledge graphs and propose FineGReS, a data-driven technique that discovers potential sub-relations with fine-grained meaning from existing pol- ysemous relations. We leverage knowledge representation learning methods that generate low-dimensional vectors (or embeddings) for knowledge graphs to capture their semantics and structure. The efficacy and utility of the proposed technique are demonstrated by comparing it with several baselines on the entity classification use case. Further, we explore the semantic representations in knowledge graph embed- ding models. In the past decade, these models have shown state-of-the-art results for the task of link prediction in the context of knowledge graph comple- tion. In view of the popularity and widespread application of the embedding techniques not only for link prediction but also for different semantic tasks, this thesis presents a critical analysis of the embeddings by quantitatively measuring their semantic capabilities. We investigate and discuss the reasons for the shortcomings of embeddings in terms of the characteristics of the underlying knowledge graph datasets and the training techniques used by popular models. Following up on this, we propose ReasonKGE, a novel method for generating semantically enriched knowledge graph embeddings by taking into account the semantics of the facts that are encapsulated by an ontology accompanying the knowledge graph. With a targeted, reasoning-based method for generating negative samples during the training of the models, ReasonKGE is able to not only enhance the link prediction performance, but also reduce the number of semantically inconsistent predictions made by the resultant embeddings, thus improving the quality of knowledge graphs.},
  language  = {en}
}
@phdthesis{Risch2020,
  author    = {Risch, Julian},
  title     = {Reader comment analysis on online news platforms},
  doi       = {10.25932/publishup-48922},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489222},
  school      = {Universit{\"a}t Potsdam},
  pages     = {xi, 135},
  year      = {2020},
  abstract  = {Comment sections of online news platforms are an essential space to express opinions and discuss political topics. However, the misuse by spammers, haters, and trolls raises doubts about whether the benefits justify the costs of the time-consuming content moderation. As a consequence, many platforms limited or even shut down comment sections completely. In this thesis, we present deep learning approaches for comment classification, recommendation, and prediction to foster respectful and engaging online discussions. The main focus is on two kinds of comments: toxic comments, which make readers leave a discussion, and engaging comments, which make readers join a discussion. First, we discourage and remove toxic comments, e.g., insults or threats. To this end, we present a semi-automatic comment moderation process, which is based on fine-grained text classification models and supports moderators. Our experiments demonstrate that data augmentation, transfer learning, and ensemble learning allow training robust classifiers even on small datasets. To establish trust in the machine-learned models, we reveal which input features are decisive for their output with attribution-based explanation methods. Second, we encourage and highlight engaging comments, e.g., serious questions or factual statements. We automatically identify the most engaging comments, so that readers need not scroll through thousands of comments to find them. The model training process builds on upvotes and replies as a measure of reader engagement. We also identify comments that address the article authors or are otherwise relevant to them to support interactions between journalists and their readership. Taking into account the readers' interests, we further provide personalized recommendations of discussions that align with their favored topics or involve frequent co-commenters. Our models outperform multiple baselines and recent related work in experiments on comment datasets from different platforms.},
  language  = {en}
}
@phdthesis{Vitagliano2024,
  author    = {Vitagliano, Gerardo},
  title     = {Modeling the structure of tabular files for data preparation},
  doi       = {10.25932/publishup-62435},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-624351},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 114},
  year      = {2024},
  abstract  = {To manage tabular data files and leverage their content in a given downstream task, practitioners often design and execute complex transformation pipelines to prepare them. The complexity of such pipelines stems from different factors, including the nature of the preparation tasks, often exploratory or ad-hoc to specific datasets; the large repertory of tools, algorithms, and frameworks that practitioners need to master; and the volume, variety, and velocity of the files to be prepared. Metadata plays a fundamental role in reducing this complexity: characterizing a file assists end users in the design of data preprocessing pipelines, and furthermore paves the way for suggestion, automation, and optimization of data preparation tasks. Previous research in the areas of data profiling, data integration, and data cleaning, has focused on extracting and characterizing metadata regarding the content of tabular data files, i.e., about the records and attributes of tables. Content metadata are useful for the latter stages of a preprocessing pipeline, e.g., error correction, duplicate detection, or value normalization, but they require a properly formed tabular input. Therefore, these metadata are not relevant for the early stages of a preparation pipeline, i.e., to correctly parse tables out of files. In this dissertation, we turn our focus to what we call the structure of a tabular data file, i.e., the set of characters within a file that do not represent data values but are required to parse and understand the content of the file. We provide three different approaches to represent file structure, an explicit representation based on context-free grammars; an implicit representation based on file-wise similarity; and a learned representation based on machine learning. In our first contribution, we use the grammar-based representation to characterize a set of over 3000 real-world csv files and identify multiple structural issues that let files deviate from the csv standard, e.g., by having inconsistent delimiters or containing multiple tables. We leverage our learnings about real-world files and propose Pollock, a benchmark to test how well systems parse csv files that have a non-standard structure, without any previous preparation. We report on our experiments on using Pollock to evaluate the performance of 16 real-world data management systems. Following, we characterize the structure of files implicitly, by defining a measure of structural similarity for file pairs. We design a novel algorithm to compute this measure, which is based on a graph representation of the files' content. We leverage this algorithm and propose Mondrian, a graphical system to assist users in identifying layout templates in a dataset, classes of files that have the same structure, and therefore can be prepared by applying the same preparation pipeline. Finally, we introduce MaGRiTTE, a novel architecture that uses self-supervised learning to automatically learn structural representations of files in the form of vectorial embeddings at three different levels: cell level, row level, and file level. We experiment with the application of structural embeddings for several tasks, namely dialect detection, row classification, and data preparation efforts estimation. Our experimental results show that structural metadata, either identified explicitly on parsing grammars, derived implicitly as file-wise similarity, or learned with the help of machine learning architectures, is fundamental to automate several tasks, to scale up preparation to large quantities of files, and to provide repeatable preparation pipelines.},
  language  = {en}
}
@phdthesis{Gruetze2018,
  author    = {Gr{\"u}tze, Toni},
  title     = {Adding value to text with user-generated content},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 114},
  year      = {2018},
  abstract  = {In recent years, the ever-growing amount of documents on the Web as well as in closed systems for private or business contexts led to a considerable increase of valuable textual information about topics, events, and entities. It is a truism that the majority of information (i.e., business-relevant data) is only available in unstructured textual form. The text mining research field comprises various practice areas that have the common goal of harvesting high-quality information from textual data. These information help addressing users' information needs. In this thesis, we utilize the knowledge represented in user-generated content (UGC) originating from various social media services to improve text mining results. These social media platforms provide a plethora of information with varying focuses. In many cases, an essential feature of such platforms is to share relevant content with a peer group. Thus, the data exchanged in these communities tend to be focused on the interests of the user base. The popularity of social media services is growing continuously and the inherent knowledge is available to be utilized. We show that this knowledge can be used for three different tasks. Initially, we demonstrate that when searching persons with ambiguous names, the information from Wikipedia can be bootstrapped to group web search results according to the individuals occurring in the documents. We introduce two models and different means to handle persons missing in the UGC source. We show that the proposed approaches outperform traditional algorithms for search result clustering. Secondly, we discuss how the categorization of texts according to continuously changing community-generated folksonomies helps users to identify new information related to their interests. We specifically target temporal changes in the UGC and show how they influence the quality of different tag recommendation approaches. Finally, we introduce an algorithm to attempt the entity linking problem, a necessity for harvesting entity knowledge from large text collections. The goal is the linkage of mentions within the documents with their real-world entities. A major focus lies on the efficient derivation of coherent links. For each of the contributions, we provide a wide range of experiments on various text corpora as well as different sources of UGC. The evaluation shows the added value that the usage of these sources provides and confirms the appropriateness of leveraging user-generated content to serve different information needs.},
  language  = {en}
}