@inproceedings{63754,
  abstract     = {{Data spaces are receiving an emerging interest in Information Systems Research and industry practice. They are central to many European research initiatives and shape the data economy in Industry 4.0. Generally, they aim to create secure environments for cross-organizational data management and sharing. Currently, there is considerable interest in developing new data spaces in Industry 4.0, also accelerated through regulatory changes. However, key questions about what precisely characterizes a data space in Industry 4.0 remain unresolved. Against this backdrop, we build a taxonomy of data spaces in the Industry 4.0 context. We identified nine distinctive dimensions and 40 corresponding characteristics among the 19 data spaces analyzed. The taxonomy enables clearer classification and nomenclature of data spaces in this context. This short paper will ignite planned further research on data spaces in Industry 4.0 and contribute to a conceptualization of a taxonomic theory for interested researchers.}},
  author       = {{Werth, Oliver and Koldewey, Christian and Uslar, Mathias and Zerbin, Julian}},
  booktitle    = {{Lecture Notes in Business Information Processing}},
  isbn         = {{9783032145178}},
  issn         = {{1865-1348}},
  keywords     = {{Industry 4.0, Taxonomy, Data spaces, Characterization}},
  location     = {{Stuttgart, Germany}},
  publisher    = {{Springer Nature Switzerland}},
  title        = {{{What Characterizes Data Spaces in Industry 4.0? Towards a Better Understanding}}},
  doi          = {{10.1007/978-3-032-14518-5_3}},
  year         = {{2026}},
}

@article{45299,
  abstract     = {{Many applications are driven by Machine Learning (ML) today. While complex ML models lead to an accurate prediction, their inner decision-making is obfuscated. However, especially for high-stakes decisions, interpretability and explainability of the model are necessary. Therefore, we develop a holistic interpretability and explainability framework (HIEF) to objectively describe and evaluate an intelligent system’s explainable AI (XAI) capacities. This guides data scientists to create more transparent models. To evaluate our framework, we analyse 50 real estate appraisal papers to ensure the robustness of HIEF. Additionally, we identify six typical types of intelligent systems, so-called archetypes, which range from explanatory to predictive, and demonstrate how researchers can use the framework to identify blind-spot topics in their domain. Finally, regarding comprehensiveness, we used a random sample of six intelligent systems and conducted an applicability check to provide external validity.}},
  author       = {{Kucklick, Jan-Peter}},
  issn         = {{1246-0125}},
  journal      = {{Journal of Decision Systems}},
  keywords     = {{Explainable AI (XAI), machine learning, interpretability, real estate appraisal, framework, taxonomy}},
  pages        = {{1--41}},
  publisher    = {{Taylor & Francis}},
  title        = {{{HIEF: a holistic interpretability and explainability framework}}},
  doi          = {{10.1080/12460125.2023.2207268}},
  year         = {{2023}},
}

@inproceedings{29539,
  abstract     = {{Explainable Artificial Intelligence (XAI) is currently an important topic for the application of Machine Learning (ML) in high-stakes decision scenarios. Related research focuses on evaluating ML algorithms in terms of interpretability. However, providing a human understandable explanation of an intelligent system does not only relate to the used ML algorithm. The data and features used also have a considerable impact on interpretability. In this paper, we develop a taxonomy for describing XAI systems based on aspects about the algorithm and data. The proposed taxonomy gives researchers and practitioners opportunities to describe and evaluate current XAI systems with respect to interpretability and guides the future development of this class of systems.}},
  author       = {{Kucklick, Jan-Peter}},
  booktitle    = {{Wirtschaftsinformatik 2022 Proceedings}},
  keywords     = {{Explainable Artificial Intelligence, XAI, Interpretability, Decision Support Systems, Taxonomy}},
  location     = {{Nürnberg (online)}},
  title        = {{{Towards a model- and data-focused taxonomy of XAI systems}}},
  year         = {{2022}},
}

@inproceedings{5661,
  abstract     = {{Spam has become one of the most annoying and costly phenomenon in the Internet. Valid e-mail addresses belong to the most valuable resources of spammers, but little is known about spammers? behavior when collecting and harvesting addresses and spammers? capabilities and interest in carefully directed, consumer-oriented marketing have not been explored yet. Gaining insight into spammers? ways to obtain and (mis)use e-mail addresses is useful in many ways, e.g. for the assessment of the effectiveness of address obscuring techniques and the usability and necessity of hiding e-mail addresses on the Internet. This paper presents a spam honeypot project in progress addressing these issues by systematically placing e-mail addresses in the Internet and analyzing received e-mails. The honeypot?s conceptual framework, its implementation, and first empirical results are presented. Finally, an outlook on further work and activities is provided.}},
  author       = {{Schryen, Guido}},
  booktitle    = {{Proceedings of the 6th IEEE Information Assurance Workshop}},
  keywords     = {{Spam, ham, e-mail, honeypot, address obscuring technique, address taxonomy}},
  pages        = {{37--41}},
  publisher    = {{Westpoint}},
  title        = {{{An e-mail honeypot addressing spammers' behavior in collecting and applying addresses}}},
  year         = {{2005}},
}