Patrick Schrottenbacher
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Patrick Schrottenbacher has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Mehler
Text Technology Lab Goethe University Frankfurt Germany
8 shared publications - Giuseppe Abrami
Goethe University Frankfurt Texttechnology Robert-Mayer-Strasse 10 60325 Frankfurt am Main
7 shared publications - Alexander Henlein
Text Technology Lab Goethe University Frankfurt Germany
3 shared publications - Juliane Engel
Goethe University Frankfurt, Texttechnology Lab
3 shared publications - Maxim Konca
Text Technology Lab, Faculty of Computer Science and Mathematics, Goethe University, Frankfurt, Germany
3 shared publications - Mevlüt Bagci
Goethe University Frankfurt, Texttechnology Lab
3 shared publications
Latest Publications
- Open Access
- 14 September 2026
- Published by Elsevier in SSRN Electronic Journal
InterView: Towards a Unified VR-Capable Interview Environment
Since surveys continue to face challenges such as attrition, recruitment difficulties, and rising costs, researchers are exploring various technological alternatives. One such alternative concerns the shift toward digital interview settings, such as video interviews .A second development builds on the growing capabilities of XR and, especially, VR systems, in which one or more interview partners are represented as virtual avatars.A third development concerns hypertext systems as an approach to modeling and representing extensible textual data structures based on the networked organization of information. Leveraging these three shifts (multimodality, XR, and informational networking), we introduce InterView: a unified interview environment that takes advantage of the multimodality of XR. It enables users to participate in interviews from virtually any platform and ensures that a wide range of multimodal signals exchanged in digital interview settings are displayed, stored in a database, networked, and made available for post-processing.InterView provides an environment specifically designed for interview-driven survey research and enables scientific insights to be derived from the analysis of structured multimodal data. We evaluate InterView through a study involving 27 participants who took part in interviews while wearing a VR headset.Our evaluation shows that InterView is usable and stable. The multimodal signals it captures - gaze, speech and response timing - reveal a measurable behavioral footprint of discomfort, in response to sensitive questionnaire items, even among participants who did not report feeling uncomfortable.This indicates that self-reporting alone would substantially underestimate such effects.
- 14 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessInterView: Towards a Unified VR-Capable Interview Environment
Since surveys continue to face challenges such as attrition, recruitment difficulties, and rising costs, researchers are exploring various technological alternatives. One such alternative concerns the shift toward digital interview settings, such as video interviews .A second development builds on the growing capabilities of XR and, especially, VR systems, in which one or more interview partners are represented as virtual avatars.A third development concerns hypertext systems as an approach to modeling and representing extensible textual data structures based on the networked organization of information. Leveraging these three shifts (multimodality, XR, and informational networking), we introduce InterView: a unified interview environment that takes advantage of the multimodality of XR. It enables users to participate in interviews from virtually any platform and ensures that a wide range of multimodal signals exchanged in digital interview settings are displayed, stored in a database, networked, and made available for post-processing.InterView provides an environment specifically designed for interview-driven survey research and enables scientific insights to be derived from the analysis of structured multimodal data. We evaluate InterView through a study involving 27 participants who took part in interviews while wearing a VR headset.Our evaluation shows that InterView is usable and stable. The multimodal signals it captures - gaze, speech and response timing - reveal a measurable behavioral footprint of discomfort, in response to sensitive questionnaire items, even among participants who did not report feeling uncomfortable.This indicates that self-reporting alone would substantially underestimate such effects.
- 2 September 2026
- Published by Springer Nature
- p. 3-22
ReEmote: Towards Emotion Representation in VR Through Va.Si.Li-Lab
- 2 September 2026
- Published by Springer Nature
- p. 3-22
ReEmote: Towards Emotion Representation in VR Through Va.Si.Li-Lab
- Open Access
- 15 July 2026
- Published by Elsevier in SSRN Electronic Journal
MMAnnotator: Enhancing the Annotation of Web Documents in the Field of Educational Sciences with a RAG Chatbot
Generative AI has led to changes in linguistic annotation. Tasks that previously required human annotation can now be automated. As LLMs become more capable, the problems they can address become more complex.LLM-based chatbots present new opportunities: annotators can ask the bot questions and request explanations within the UI. This is highly relevant for multimodal annotation, given that only a few platforms support the annotation of different modalities.We introduce MMAnnotator, a MultiMedia annotation system aiming to fill this gap. It allows for linguistic and multimodal annotation with the help of a chatbot. We demonstrate MMAnnotator in the field of educational sciences and provide a user study for evaluation.
- 15 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMMAnnotator: Enhancing the Annotation of Web Documents in the Field of Educational Sciences with a RAG Chatbot
Generative AI has led to changes in linguistic annotation. Tasks that previously required human annotation can now be automated. As LLMs become more capable, the problems they can address become more complex.LLM-based chatbots present new opportunities: annotators can ask the bot questions and request explanations within the UI. This is highly relevant for multimodal annotation, given that only a few platforms support the annotation of different modalities.We introduce MMAnnotator, a MultiMedia annotation system aiming to fill this gap. It allows for linguistic and multimodal annotation with the help of a chatbot. We demonstrate MMAnnotator in the field of educational sciences and provide a user study for evaluation.
- Open Access
- 10 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 153-166
Measuring Group Creativity of Dialogic Interaction Systems by Means of Remote Entailment Analysis
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.
- 10 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 153-166
Open AccessMeasuring Group Creativity of Dialogic Interaction Systems by Means of Remote Entailment Analysis
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.
- 5 August 2024
- Published by Springer Nature
- p. 259-303
Towards New Data Spaces for the Study of Multiple Documents with Va.Si.Li-Lab: A Conceptual Analysis
- 5 August 2024
- Published by Springer Nature
- p. 259-303
Towards New Data Spaces for the Study of Multiple Documents with Va.Si.Li-Lab: A Conceptual Analysis
- Open Access
- 4 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Va.Si.Li-Lab as a collaborative multi-user annotation tool in virtual reality and its potential fields of application
- 4 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessVa.Si.Li-Lab as a collaborative multi-user annotation tool in virtual reality and its potential fields of application
- 9 July 2023
- Published by Springer Nature
- p. 539-565
A Multimodal Data Model for Simulation-Based Learning with Va.Si.Li-Lab
- 9 July 2023
- Published by Springer Nature
- p. 539-565
A Multimodal Data Model for Simulation-Based Learning with Va.Si.Li-Lab