As conversational search becomes more pervasive, it becomes increasingly important to understand the users’ underlying information needs when they converse with such systems in diverse domains. We conduct an in situ study to understand information needs arising in a home cooking context as well as how they are verbally communicated to an assistant. A human experimenter plays this role in our study. Based on the transcriptions of utterances, we derive a detailed hierarchical taxonomy of diverse information needs occurring in this context, which require different levels of assistance to be solved. The taxonomy shows that needs can be communicated through different linguistic means and require different amounts of context to be understood. In a second contribution, we perform classification experiments to determine the feasibility of predicting the type of information need a user has during a dialogue using the turn provided. For this multi-label classification problem, we achieve average F1 measures of 40% using BERT-based models. We demonstrate with examples which types of needs are difficult to predict and show why, concluding that models need to include more context information in order to improve both information need classification and assistance to make such systems usable.

In this paper a holistic approach for developing indoor pedestrian navigation systems is described: first of all, a map modeling toolkit is introduced that allows for the simple and fast creation of environment models and calculation of preference-ba

Purpose: Performing tasks in public spaces can be demanding due to task complexity. Systems that can keep track of the current task state may help their users to successfully fulfill a task. These systems, however, require major implementation effort. The purpose of this paper is to investigate if and how a mobile information assistant which has only basic task-tracking capabilities can support users by employing a least effort approach. This means, we are interested in whether such a system is able to have an impact on the way a workflow in public space is perceived. Design/methodology/approach: The authors implement and test AIRBOT, a mobile chatbot application that can assist air passengers in successfully boarding a plane. The authors apply a three-tier approach and, first, conduct expert and passenger interviews to understand the workflow and the information needs occurring therein; second, the authors implement a mobile chatbot application providing minimum task-tracking capabilities to support travelers by providing boarding-relevant information in a proactive manner. Finally, the authors evaluate this application by means of an in situ study (n = 101 passengers) at a major European airport. Findings: The authors provide evidence that basic task-tracking capabilities are sufficient to affect the users’ task perception. AIRBOT is able to decrease the perceived workload airport services impose on users. It has a negative impact on satisfaction with non-personalized information offered by the airport, though. Originality/value: The study shows that the number of features is not the most important means to successfully provide assistance in public space workflows. The study can, moreover, serve as a blueprint to design task-based assistants for other contexts.

In this report, we present the project URWalking conducted at the University of Regensburg. We describe its major outcomes: Firstly, an indoor navigation system for pedestrians as a web application and as an Android app with position tracking of users in indoor and outdoor environments. Our implementation showcases that a variant of the $$A^*$$A ∗ -algorithm by Ullmann (tengetriebene optimierung präferenzadaptiver fußwegrouten durch gebäudekomplexe https://epub.uni-regensburg.de/43697/, 2020) can handle the routing problem in large, levelled indoor environments efficiently. Secondly, the apps have been used in several studies for a deeper understanding of human wayfinding. We collected eye tracking and synchronized video data, think aloud protocols, and log data of users interacting with the apps. We applied state-of-the-art deep learning models for gaze tracking and automatic classification of landmarks. Our results indicate that even the most recent version of the YOLO image classifier by Redmon and Farhadi (olov3: An incremental improvement. arXiv, 2018) needs finetuning to recognize everyday objects in indoor environments. Furthermore, we provide empirical evidence that appropriate machine learning models are helpful to bridge behavioural data from users during wayfinding and conceptual models for the salience of objects and landmarks. However, simplistic models are insufficient to reasonably explain wayfinding behaviour in real time—an open issue in GeoAI. We conclude that the GeoAI community should collect more naturalistic log data of wayfinding activities in order to build efficient machine learning models capable of predicting user reactions to routing instructions and of explaining how humans integrate stimuli from the environment as essential information into routing instructions while solving wayfinding tasks. Such models form the basis for real-time wayfinding assistance.