Teamwork is a crucial strategy for solving a common problem in a collaborative search in a professional environment. Information systems for collaborative search are based on advanced visualizations and/or "classical" principles of human-machine interaction (HMI). Machine learning techniques also play a role. The goal of developing systems for collaborative search is to support the individual user in tasks such as formulating queries based on keywords. In addition, users should be supported to share search-relevant information within a team and to derive knowledge jointly. In this scenario, the open research question is how to increase the adoption of information systems for collaborative search. Recent research results show that human-machine teaming (HMT) - a specific topic of HMI - could be a promising solution approach. HMT requires that humans perceive a machine as a trusted and valuable team partner that contributes to the solution of a shared task.
In HMT research, it is still being determined how systems can be designed so that their users perceive them as team partners. It can be difficult for users to develop trust in the processes and results of machine learning - which is often a capability of an information system - if the logic behind the results is not communicated naturally. This is where research focuses on explainable artificial intelligence (XAI) and transparency rather than black boxes. However, the lack of ground truth makes the development of XAI difficult. To broaden the perspective of XAI and increase confidence, we explore interactive multimodal data representations and attention-focusing support techniques. In addition, we develop data-driven behavioral models that are used to anticipate human (search) behavior. Thus, we provide systems with a fundamental capability for (joint) problem solving in HMT.
Research is conducted with partners in the CHIM research and innovation network.
- F. Klein, J. Höbel-Müller, S. Polley, S. Werner, A. Nürnberger: Navigating a Search Map using Audible Landmarks in Virtual Reality. In: Proceedings of DAGA 2023 - Berlin, Deutsche Gesellschaft für Akustik e.V., pp. 1617-1619. https://pub.dega-akustik.de/DAGA_2023/data/index.html
- V. Obionwu, A. Nürnberger, G. Saake: Enhancing Team Collaboration and Knowledge Exchange through a Skill Sharing Platform. In: Proceedings of the 18th International Conference on Web Information Systems and Technologies (WEBIST 2022), pp. 365-372.
- J. Schwerdt, A. Nürnberger: Detecting Automatic Reading Behavior During Online Search Sessions. In: Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization, Barcelona, Spain, July 4 - 7, 2022, pp. 13-17. New York, NY, United States: Association for Computing Machinery, 2022. https://doi.org/10.1145/3511047.3536418
- M. Spiller, Y. Liu, M. Z. Hossain, T. Gedeon, J. Geissler, A. Nürnberger: Enhancing User-Adaptive Information Visualization Systems through Predicting Visual Search Task Success from Eye Gaze Data. ACM Transactions on Interactive Intelligent Systems (2021), 11(2), pp. 1-25. https://doi.org/10.1145/3446638