Design principles for conversational agents to support Emergency Management Agencies

Stefan Stieglitz; Lennart Hofeditz; Felix Brünker; Christian Ehnis; Milad Mirbabaie; Björn Ross

doi:10.1016/j.ijinfomgt.2021.102469

Design principles for conversational agents to support Emergency Management Agencies

Int J Inf Manage. 2022 Apr:63:102469. doi: 10.1016/j.ijinfomgt.2021.102469. Epub 2022 Jan 13.

Authors

Stefan Stieglitz¹, Lennart Hofeditz¹, Felix Brünker¹, Christian Ehnis², Milad Mirbabaie³, Björn Ross⁴

Affiliations

¹ Digital Communication and Transformation, Department of Computer Science and Applied Cognitive Science, Faculty of Engineering, University of Duisburg-Essen, Forsthausweg 2, 47057 Duisburg, Germany.
² The University of Sydney Business School, The University of Sydney, Rm 4053, Level 4, Abercrombie Building H70, NSW 2006, Australia.
³ Paderborn University, Warburger Str. 100, (Q3.128), 33098 Paderborn, Germany.
⁴ University of Edinburgh, Informatics Forum, 10 Crichton St, Edinburgh EH8 9AB, UK.

Abstract

Widespread mis- and disinformation during the COVID-19 social media "infodemic" challenge the effective response of Emergency Management Agencies (EMAs). Conversational Agents (CAs) have the potential to amplify and distribute trustworthy information from EMAs to the general public in times of uncertainty. However, the structure and responsibilities of such EMAs are different in comparison to traditional commercial organizations. Consequently, Information Systems (IS) design approaches for CAs are not directly transferable to this different type of organization. Based on semi-structured interviews with practitioners from EMAs in Germany and Australia, twelve meta-requirements and five design principles for CAs for EMAs were developed. In contrast to the traditional view of CA design, social cues should be minimized. The study provides a basis to design robust CAs for EMAs.

Keywords: Chatbots; Conversational agents; Crisis communication; Design principles.