CORE C08

@inproceedings{Schaaf:et:al:2026,
  title     = {{GhostWriter}: Hidden {AI}-Generated Texts Over Multiple Languages,
               Domains and Generators},
  booktitle = {Proceedings of the 15th International Conference on Language Resources
               and Evaluation (LREC 2026)},
  year      = {2026},
  author    = {Schaaf, Manuel and Bönisch, Kevin and Mehler, Alexander},
  keywords  = {Corpus, Natural Language Generation; Validation of LRs, AI-generated Text Detection, core, core_b05},
  abstract  = {The advent of Transformer-based Large Language Models (LLMs) has
               led to an unprecedented surge of AI-generated text (AIGT) across
               online platforms and academic domains. While these models exhibit
               near-human fluency and stylistic coherence, their widespread adoption
               has raised concerns about authorship integrity, research quality,
               and the recursive contamination of training corpora with synthetic
               data. These developments underscore the need for reliable AIGT
               detection methods and benchmark datasets, particularly for malicious
               or deceptive ghostwriting scenarios where AIGT is intentionally
               crafted to evade detection. To address this, we present GhostWriter,
               a large-scale, bilingual (German and English), multi-generator,
               and multi-domain dataset for AIGT detection. The dataset comprises
               human- and AI-authored texts produced under domain-specific ghostwriting
               conditions, including examples intentionally embedded within otherwise
               human-written texts to obscure their AI origin. With GhostWriter,
               we (i) aim to expand the resources available for German AIGT datasets,
               (ii) emphasize mixed or fused synthesizations---since most existing
               corpora are limited to the document level---and (iii) introduce
               specifically crafted malicious ghostwriting scenarios across multiple
               domains and generators.},
  note      = {accepted}
}

@inproceedings{Bisang:Mehler:2026,
  title     = {Linguistic Features as Predictors of Students' Performance in
               Domain-Specific Critical Online Reasoning Tasks},
  author    = {Bisang, Walter and Mehler, Alexander},
  booktitle = {International Test Commission Conference (ITC) 2026},
  eventdate = {2026-06-30/2026-07-03},
  location  = {Auckland, New Zealand},
  note      = {accepted},
  year      = {2026},
  keywords  = {core,core_b05}
}

@article{Borkowski:et:al:2026,
  title     = {{DUUIgateway}: A Web Service for Platform-independent, Ubiquitous Big Data NLP},
  journal   = {SoftwareX},
  volume    = {34},
  pages     = {102549},
  year      = {2026},
  issn      = {2352-7110},
  doi       = {https://doi.org/10.1016/j.softx.2026.102549},
  url       = {https://www.sciencedirect.com/science/article/pii/S2352711026000439},
  author    = {Borkowski, Cedric and Abrami, Giuseppe and Terefe, Dawit and Baumartz, Daniel
               and Mehler, Alexander},
  keywords  = {duui, neglab, core, core_b05, core_c08, new-data-spaces, circlet},
  abstract  = {Distributed processing of unstructured text data is a challenge
               in the rapidly changing and evolving natural language processing
               (NLP) landscape. This landscape is characterized by heterogeneous
               systems, models, and formats, and especially by the increasing
               influence of AI systems. While many of these systems handle text
               data, there are also unified systems that process multiple input
               and output formats, while allowing for distributed corpus processing.
               However, there are hardly any user-friendly interfaces that allow
               existing NLP frameworks to be used flexibly and extended in a
               user-controlled manner. Due to this gap and the increasing importance
               of NLP for various scientific disciplines, there has been a demand
               for a web and API based flexible software solution for deploying,
               managing and monitoring NLP systems. Such a solution is provided
               by Docker Unified UIMA-gateway. We introduce DUUIgateway and evaluate
               its API and user-driven approach to encapsulation. We also describe
               how these features improve the usability and accessibility of
               the NLP framework DUUI. We illustrate DUUIgateway in the field
               of process modeling in higher education and show how it closes
               the latter gap in NLP by making a variety of systems for processing
               text and multimodal data accessible to non-experts.}
}

@article{Mehler:et:al:2026:a,
  title     = {Linguistic Features of Student Responses as Indicators of Performance
               in Critical Online Reasoning Tasks},
  author    = {Alexander Mehler and Walter Bisang and Maxim Konca and Patryik Czerwinski
               and Jeremias Josef Graf and Jana Fritsch},
  journal   = {Zeitschrift für Erziehungswissenschaft},
  note      = {accepted},
  year      = {2026},
  publisher = {Springer},
  keywords  = {core,core_b05}
}

@inproceedings{Boenisch:et:al:2025,
  title     = {Towards Unified, Dynamic and Annotation-based Visualisations and
               Exploration of Annotated Big Data Corpora with the Help of Unified
               Corpus Explorer},
  author    = {B{\"o}nisch, Kevin and Abrami, Giuseppe and Mehler, Alexander},
  editor    = {Dziri, Nouha and Ren, Sean (Xiang) and Diao, Shizhe},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas
               Chapter of the Association for Computational Linguistics: Human
               Language Technologies (System Demonstrations)},
  year      = {2025},
  address   = {Albuquerque, New Mexico},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2025.naacl-demo.42/},
  pages     = {522--534},
  isbn      = {979-8-89176-191-9},
  abstract  = {The annotation and exploration of large text corpora, both automatic
               and manual, presents significant challenges across multiple disciplines,
               including linguistics, digital humanities, biology, and legal
               science. These challenges are exacerbated by the heterogeneity
               of processing methods, which complicates corpus visualization,
               interaction, and integration. To address these issues, we introduce
               the Unified Corpus Explorer (UCE), a standardized, dockerized,
               open-source and dynamic Natural Language Processing (NLP) application
               designed for flexible and scalable corpus navigation. Herein,
               UCE utilizes the UIMA format for NLP annotations as a standardized
               input, constructing interfaces and features around those annotations
               while dynamically adapting to the corpora and their extracted
               annotations. We evaluate UCE based on a user study and demonstrate
               its versatility as a corpus explorer based on generative AI.},
  note      = {Best Demo Award},
  pdf       = {https://aclanthology.org/2025.naacl-demo.42.pdf},
  keywords  = {uce,new-data-spaces,circlet,core,core_c08}
}

@article{Abrami:et:al:2025:a,
  title     = {Docker Unified UIMA Interface: New perspectives for NLP on big data},
  journal   = {SoftwareX},
  volume    = {29},
  pages     = {102033},
  year      = {2025},
  issn      = {2352-7110},
  doi       = {https://doi.org/10.1016/j.softx.2024.102033},
  url       = {https://www.sciencedirect.com/science/article/pii/S2352711024004047},
  author    = {Giuseppe Abrami and Markos Genios and Filip Fitzermann and Daniel Baumartz
               and Alexander Mehler},
  keywords  = {Docker, Kubernetes, UIMA, Distributed NLP, duui, biofid, neglab, new-data-spaces, circlet, core, core_c08},
  abstract  = {Processing large amounts of natural language text using machine
               learning-based models is becoming important in many disciplines.
               This demand is being met by a variety of approaches, resulting
               in the heterogeneous deployment of separate, partly incompatible,
               not natively scalable applications. To overcome the technological
               bottleneck involved, we have developed Docker Unified UIMA Interface,
               a system for the standardized, parallel, platform-independent,
               distributed and microservices-based solution for processing large
               and extensive text corpora with any NLP method. We present DUUI
               as a framework that enables automated orchestration of GPU-based
               NLP processes beyond the existing Docker Swarm cluster variant,
               and in addition to the adaptation to new runtime environments
               such as Kubernetes. Therefore, a new driver for DUUI is introduced,
               which enables the lightweight orchestration of DUUI processes
               within a Kubernetes environment in a scalable setup. In this way,
               the paper opens up novel text-technological perspectives for existing
               practices in disciplines that deal with the scientific analysis
               of large amounts of data based on NLP.}
}

@inproceedings{Abrami:et:al:2025:b,
  author    = {Abrami, Giuseppe and Baumartz, Daniel and Mehler, Alexander},
  title     = {DUUI: A Toolbox for the Construction of a new Kind of Natural
               Language Processing},
  year      = {2025},
  booktitle = {Proceedings of the DHd 2025: Under Construction. Geisteswissenschaften
               und Data Humanities},
  numpages  = {3},
  location  = {Bielefeld, Germany},
  series    = {DHd 2025},
  publisher = {Zenodo},
  keywords  = {duui,core,core_c08},
  pages     = {446--448},
  doi       = {10.5281/zenodo.14943128},
  url       = {https://doi.org/10.5281/zenodo.14943128},
  poster    = {https://zenodo.org/records/14944575}
}

@inbook{Mehler:et:al:2024:a,
  author    = {Mehler, Alexander and Bagci, Mevl{\"u}t and Schrottenbacher, Patrick
               and Henlein, Alexander and Konca, Maxim and Abrami, Giuseppe and B{\"o}nisch, Kevin
               and Stoeckel, Manuel and Spiekermann, Christian and Engel, Juliane},
  editor    = {Zlatkin-Troitschanskaia, Olga and Nagel, Marie-Theres and Klose, Verena
               and Mehler, Alexander},
  title     = {Towards New Data Spaces for the Study of Multiple Documents with
               Va.Si.Li-Lab: A Conceptual Analysis},
  booktitle = {Students', Graduates' and Young Professionals' Critical Use of
               Online Information: Digital Performance Assessment and Training
               within and across Domains},
  year      = {2024},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {259--303},
  abstract  = {The constitution of multiple documents has so far been studied
               essentially as a process in which a single learner consults a
               number (of segments) of different documents in the context of
               the task at hand in order to construct a mental model for the
               purpose of completing the task. As a result of this research focus,
               the constitution of multiple documents appears predominantly as
               a monomodal, non-interactive process in which mainly textual units
               are studied, supplemented by images, text-image relations and
               comparable artifacts. This approach is reflected in the contextual
               fixity of the research design, in which the learners under study
               search for information using suitably equipped computers. If,
               on the other hand, we consider the openness of multi-agent learning
               situations, this scenario lacks the aspects of interactivity,
               contextual openness and, above all, the multimodality of information
               objects, information processing and information exchange. This
               is where the chapter comes in. It describes Va.Si.Li-Lab as an
               instrument for multimodal measurement for studying and modeling
               multiple documents in the context of interactive learning in a
               multi-agent environment. To this end, the chapter places Va.Si.Li-Lab
               in the spectrum of evolutionary approaches that vary the combination
               of human and machine innovation and selection. It also combines
               the requirements of multimodal representational learning with
               various aspects of contextual plasticity to prepare Va.Si.Li-Lab
               as a system that can be used for experimental research. The chapter
               is conceptual in nature, designing a system of requirements using
               the example of Va.Si.Li-Lab to outline an experimental environment
               in which the study of Critical Online Reasoning (COR) as a group
               process becomes possible. Although the chapter illustrates some
               of these requirements with realistic data from the field of simulation-based
               learning, the focus is still conceptual rather than experimental,
               hypothesis-driven. That is, the chapter is concerned with the
               design of a technology for future research into COR processes.},
  isbn      = {978-3-031-69510-0},
  doi       = {10.1007/978-3-031-69510-0_12},
  url       = {https://doi.org/10.1007/978-3-031-69510-0_12},
  keywords  = {core, core_c08}
}

@inproceedings{Baumartz:et:al:2024,
  author    = {Baumartz, Daniel and Konca, Maxim and Mehler, Alexander and Schrottenbacher, Patrick
               and Braunheim, Dominik},
  title     = {Measuring Group Creativity of Dialogic Interaction Systems by
               Means of Remote Entailment Analysis},
  year      = {2024},
  isbn      = {9798400705953},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3648188.3675140},
  doi       = {10.1145/3648188.3675140},
  abstract  = {We present a procedure for assessing group creativity that allows
               us to compare the contributions of human interlocutors and chatbots
               based on generative AI such as ChatGPT. We focus on everyday creativity
               in terms of dialogic communication and test four hypotheses about
               the difference between human and artificial communication. Our
               procedure is based on a test that requires interlocutors to cooperatively
               interpret a sequence of sentences for which we control for coherence
               gaps with reference to the notion of entailment. Using NLP methods,
               we automatically evaluate the spoken or written contributions
               of interlocutors (human or otherwise). The paper develops a routine
               for automatic transcription based on Whisper, for sampling texts
               based on their entailment relations, for analyzing dialogic contributions
               along their semantic embeddings, and for classifying interlocutors
               and interaction systems based on them. In this way, we highlight
               differences between human and artificial conversations under conditions
               that approximate free dialogic communication. We show that despite
               their obvious classificatory differences, it is difficult to see
               clear differences even in the domain of dialogic communication
               given the current instruments of NLP.},
  booktitle = {Proceedings of the 35th ACM Conference on Hypertext and Social Media},
  pages     = {153–-166},
  numpages  = {14},
  keywords  = {Creative AI, Creativity, Generative AI, Hermeneutics, NLP, core, core_b05, core_c08},
  location  = {Poznan, Poland},
  series    = {HT '24}
}

@inproceedings{Abrami:Mehler:2024,
  author    = {Abrami, Giuseppe and Mehler, Alexander},
  title     = {Efficient, uniform and scalable parallel NLP pre-processing with
               DUUI: Perspectives and Best Practice for the Digital Humanities},
  year      = {2024},
  month     = {08},
  editor    = {Karajgikar, Jajwalya and Janco, Andrew and Otis, Jessica},
  booktitle = {Digital Humanities Conference 2024 - Book of Abstracts (DH 2024)},
  location  = {Washington, DC, USA},
  series    = {DH},
  keywords  = {duui, core, core_c08},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.13761079},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/12/DH2024_Poster.pdf},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2024/12/DH2024_Abstract.pdf},
  url       = {https://doi.org/10.5281/zenodo.13761079},
  pages     = {15--18},
  numpages  = {4}
}

@inproceedings{Leonhardt:et:al:2023,
  title     = {Unlocking the Heterogeneous Landscape of Big Data {NLP} with {DUUI}},
  author    = {Leonhardt, Alexander and Abrami, Giuseppe and Baumartz, Daniel
               and Mehler, Alexander},
  editor    = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},
  year      = {2023},
  address   = {Singapore},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2023.findings-emnlp.29},
  pages     = {385--399},
  pdf       = {https://aclanthology.org/2023.findings-emnlp.29.pdf},
  abstract  = {Automatic analysis of large corpora is a complex task, especially
               in terms of time efficiency. This complexity is increased by the
               fact that flexible, extensible text analysis requires the continuous
               integration of ever new tools. Since there are no adequate frameworks
               for these purposes in the field of NLP, and especially in the
               context of UIMA, that are not outdated or unusable for security
               reasons, we present a new approach to address the latter task:
               Docker Unified UIMA Interface (DUUI), a scalable, flexible, lightweight,
               and feature-rich framework for automatic distributed analysis
               of text corpora that leverages Big Data experience and virtualization
               with Docker. We evaluate DUUI{'}s communication approach against
               a state-of-the-art approach and demonstrate its outstanding behavior
               in terms of time efficiency, enabling the analysis of big text
               data.},
  keywords  = {duui, core, core_c08}
}