@inproceedings{BuesgenKloeserKohletal.2022, author = {B{\"u}sgen, Andr{\´e} and Kl{\"o}ser, Lars and Kohl, Philipp and Schmidts, Oliver and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Exploratory analysis of chat-based black market profiles with natural language processing}, series = {Proceedings of the 11th International Conference on Data Science, Technology and Applications}, booktitle = {Proceedings of the 11th International Conference on Data Science, Technology and Applications}, isbn = {978-989-758-583-8}, issn = {2184-285X}, doi = {10.5220/0011271400003269}, pages = {83 -- 94}, year = {2022}, abstract = {Messenger apps like WhatsApp or Telegram are an integral part of daily communication. Besides the various positive effects, those services extend the operating range of criminals. Open trading groups with many thousand participants emerged on Telegram. Law enforcement agencies monitor suspicious users in such chat rooms. This research shows that text analysis, based on natural language processing, facilitates this through a meaningful domain overview and detailed investigations. We crawled a corpus from such self-proclaimed black markets and annotated five attribute types products, money, payment methods, user names, and locations. Based on each message a user sends, we extract and group these attributes to build profiles. Then, we build features to cluster the profiles. Pretrained word vectors yield better unsupervised clustering results than current state-of-the-art transformer models. The result is a semantically meaningful high-level overview of the user landscape of black market chatrooms. Additionally, the extracted structured information serves as a foundation for further data exploration, for example, the most active users or preferred payment methods.}, language = {en} } @inproceedings{BuesgenKloeserKohletal.2023, author = {B{\"u}sgen, Andr{\´e} and Kl{\"o}ser, Lars and Kohl, Philipp and Schmidts, Oliver and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {From cracked accounts to fake IDs: user profiling on German telegram black market channels}, series = {Data Management Technologies and Applications}, booktitle = {Data Management Technologies and Applications}, editor = {Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-37889-8 (Print)}, doi = {10.1007/978-3-031-37890-4_9}, pages = {176 -- 202}, year = {2023}, abstract = {Messenger apps like WhatsApp and Telegram are frequently used for everyday communication, but they can also be utilized as a platform for illegal activity. Telegram allows public groups with up to 200.000 participants. Criminals use these public groups for trading illegal commodities and services, which becomes a concern for law enforcement agencies, who manually monitor suspicious activity in these chat rooms. This research demonstrates how natural language processing (NLP) can assist in analyzing these chat rooms, providing an explorative overview of the domain and facilitating purposeful analyses of user behavior. We provide a publicly available corpus of annotated text messages with entities and relations from four self-proclaimed black market chat rooms. Our pipeline approach aggregates the extracted product attributes from user messages to profiles and uses these with their sold products as features for clustering. The extracted structured information is the foundation for further data exploration, such as identifying the top vendors or fine-granular price analyses. Our evaluation shows that pretrained word vectors perform better for unsupervised clustering than state-of-the-art transformer models, while the latter is still superior for sequence labeling.}, language = {en} } @article{HackerKraftZoell2011, author = {Hacker, Tobias and Kraft, Bodo and Z{\"o}ll, Axel}, title = {Projektzuschnitt f{\"u}r die inkrementelle Systementwicklung im Konzernverbund}, isbn = {978-3-8322-9990-3}, pages = {78 -- 83}, year = {2011}, language = {de} } @inproceedings{HeerRedkowitzKraft2008, author = {Heer, Thomas and Redkowitz, Daniel and Kraft, Bodo}, title = {Tool Support for the Integration of Light-Weight Ontologies}, isbn = {978-3-642-00670-8}, year = {2008}, abstract = {Abstract of the authors: In many areas of computer science ontologies become more and more important. The use of ontologies for domain modeling often brings up the issue of ontology integration. The task of merging several ontologies, covering specific subdomains, into one united ontology has to be solved. Many approaches for ontology integration aim at automating the process of ontology alignment. However, a complete automation is not feasible, and user interaction is always required. Nevertheless, most ontology integration tools offer only very limited support for the interactive part of the integration process. In this paper, we present a novel approach for the interactive integration of ontologies. The result of the ontology integration is incrementally updated after each definition of a correspondence between ontology elements. The user is guided through the ontologies to be integrated. By restricting the possible user actions, the integrity of all defined correspondences is ensured by the tool we developed. We evaluated our tool by integrating different regulations concerning building design.}, subject = {Ontologie }, language = {de} } @inproceedings{KirchhofKraft2004, author = {Kirchhof, M. and Kraft, Bodo}, title = {UML-based modeling of architectural knowledge and design}, year = {2004}, abstract = {IASSE-2004 - 13th International Conference on Intelligent and Adaptive Systems and Software Engineering eds. W. Dosch, N. Debnath, pp. 245-250, ISCA, Cary, NC, 1-3 July 2004, Nice, France We introduce a UML-based model for conceptual design support in civil engineering. Therefore, we identify required extensions to standard UML. Class diagrams are used for elaborating building typespecific knowledge: Object diagrams, implicitly contained in the architect's sketch, are validated against the defined knowledge. To enable the use of industrial, domain-specific tools, we provide an integrated conceptual design extension. The developed tool support is based on graph rewriting. With our approach architects are enabled to deal with semantic objects during early design phase, assisted by incremental consistency checks.}, subject = {UML}, language = {en} } @article{KirchhofKraft2012, author = {Kirchhof, Michael and Kraft, Bodo}, title = {Hybrides Vorgehensmodell : Agile und klassische Methoden im Projekt passend kombinieren}, series = {ProjektMagazin}, journal = {ProjektMagazin}, number = {11}, publisher = {Berleb Media}, address = {Taufkirchen}, pages = {11 S.}, year = {2012}, abstract = {Agil ist im Trend und immer mehr Unternehmen, die ihre Projekte bisher nach klassischen Prinzipien durchf{\"u}hrten, denken {\"u}ber den Einsatz agiler Methoden nach. Doch selbst wenn die Organisation bereits beide Philosophien unterst{\"u}tzt, gilt f{\"u}r ein Projekt meist die klare Vorgabe: agil oder klassisch. Es gibt aber noch einen anderen Ansatz, mit diesen "unterschiedlichen Welten" umzugehen: Und zwar die beiden Philosophien innerhalb eines Projekts zu kombinieren. Wie dies in der Praxis aussehen und gelingen kann, zeigen Dr. Michael Kirchhof und Prof. Dr. Bodo Kraft in diesem Beitrag.}, language = {de} } @inproceedings{KirchhofKraft2011, author = {Kirchhof, Michael and Kraft, Bodo}, title = {Dogmatisches „Entweder agil oder klassisch" im Projektmanagement hat ausgedient - die richtige Mischung macht's}, series = {Projekt-Sternstunden : strahlende Erfolge durch Kompetenz}, booktitle = {Projekt-Sternstunden : strahlende Erfolge durch Kompetenz}, publisher = {GPM}, address = {N{\"u}rnberg}, isbn = {978-3-924841-60-7}, pages = {414 -- 425}, year = {2011}, language = {de} } @inproceedings{KloeserBuesgenKohletal.2023, author = {Kl{\"o}ser, Lars and B{\"u}sgen, Andr{\´e} and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Explaining relation classification models with semantic extents}, series = {DeLTA 2023: Deep Learning Theory and Applications}, booktitle = {DeLTA 2023: Deep Learning Theory and Applications}, editor = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-39058-6 (Print)}, doi = {10.1007/978-3-031-39059-3_13}, pages = {189 -- 208}, year = {2023}, abstract = {In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relation classification. State-of-the-art systems are highly accurate on scientific benchmarks. A lack of explainability is currently a complicating factor in many real-world applications. Comprehensible systems are necessary to prevent biased, counterintuitive, or harmful decisions. We introduce semantic extents, a concept to analyze decision patterns for the relation classification task. Semantic extents are the most influential parts of texts concerning classification decisions. Our definition allows similar procedures to determine semantic extents for humans and models. We provide an annotation tool and a software framework to determine semantic extents for humans and models conveniently and reproducibly. Comparing both reveals that models tend to learn shortcut patterns from data. These patterns are hard to detect with current interpretability methods, such as input reductions. Our approach can help detect and eliminate spurious decision patterns during model development. Semantic extents can increase the reliability and security of natural language processing systems. Semantic extents are an essential step in enabling applications in critical areas like healthcare or finance. Moreover, our work opens new research directions for developing methods to explain deep learning models.}, language = {en} } @inproceedings{KloeserKohlKraftetal.2021, author = {Kl{\"o}ser, Lars and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Multi-attribute relation extraction (MARE): simplifying the application of relation extraction}, series = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA}, booktitle = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications - DeLTA}, isbn = {978-989-758-526-5}, doi = {10.5220/0010559201480156}, pages = {148 -- 156}, year = {2021}, abstract = {Natural language understanding's relation extraction makes innovative and encouraging novel business concepts possible and facilitates new digitilized decision-making processes. Current approaches allow the extraction of relations with a fixed number of entities as attributes. Extracting relations with an arbitrary amount of attributes requires complex systems and costly relation-trigger annotations to assist these systems. We introduce multi-attribute relation extraction (MARE) as an assumption-less problem formulation with two approaches, facilitating an explicit mapping from business use cases to the data annotations. Avoiding elaborated annotation constraints simplifies the application of relation extraction approaches. The evaluation compares our models to current state-of-the-art event extraction and binary relation extraction methods. Our approaches show improvement compared to these on the extraction of general multi-attribute relations.}, language = {en} } @inproceedings{KohlFreyerKraemeretal.2023, author = {Kohl, Philipp and Freyer, Nils and Kr{\"a}mer, Yoka and Werth, Henri and Wolf, Steffen and Kraft, Bodo and Meinecke, Matthias and Z{\"u}ndorf, Albert}, title = {ALE: a simulation-based active learning evaluation framework for the parameter-driven comparison of query strategies for NLP}, series = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science}, booktitle = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science}, editor = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-39058-6 (Print)}, doi = {978-3-031-39059-3}, pages = {235 -- 253}, year = {2023}, abstract = {Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process. To mitigate this challenge, Active Learning (AL) proposes promising data points to annotators they annotate next instead of a subsequent or random sample. This method is supposed to save annotation effort while maintaining model performance. However, practitioners face many AL strategies for different tasks and need an empirical basis to choose between them. Surveys categorize AL strategies into taxonomies without performance indications. Presentations of novel AL strategies compare the performance to a small subset of strategies. Our contribution addresses the empirical basis by introducing a reproducible active learning evaluation (ALE) framework for the comparative evaluation of AL strategies in NLP. The framework allows the implementation of AL strategies with low effort and a fair data-driven comparison through defining and tracking experiment parameters (e.g., initial dataset size, number of data points per query step, and the budget). ALE helps practitioners to make more informed decisions, and researchers can focus on developing new, effective AL strategies and deriving best practices for specific use cases. With best practices, practitioners can lower their annotation costs. We present a case study to illustrate how to use the framework.}, language = {en} }