TY - CHAP A1 - Rötzel, Peter T1 - Künstliche Intelligenz (KI) – unser bester Freund? Wie Menschen auf KI-Entscheidungsempfehlungen reagieren T2 - Vertrauen in Künstliche Intelligenz N2 - Künstliche Intelligenz (KI) hat sich zu einer transformativen Kraft entwickelt, die verschiedene Aspekte der täglichen Arbeit beeinflusst. Es stellt sich die Frage: Können Menschen freundschaftliche Beziehungen zu KI-Entscheidungsunterstützungssystemen aufbauen oder werden diese Systeme nur als Werkzeuge betrachtet? In diesem Kapitel werden die Dynamik, die Herausforderungen und die Möglichkeiten von Mensch-KI-Interaktionen (MKI) untersucht, wobei ein besonderer Fokus auf die entscheidende Rolle des Vertrauens in dieser Interaktion gelegt wird. Das Vertrauen in KI wird durch kognitive, emotionale und soziale Faktoren beeinflusst. Zu den kognitiven Faktoren gehören die Transparenz und Interpretierbarkeit von KI-Systemen, zu den emotionalen Faktoren gehören die emotionale Bindung und das Verhältnis zwischen Menschen und KI-Agenten und zu den sozialen Faktoren gehören gesellschaftliche Normen und kulturelle Einflüsse. Das Spannungsverhältnis zwischen Automatisierungs- und Algorithmusvermeidungstendenzen stellt eine komplexe Herausforderung für MKI dar. Automatisierungsbias bedeutet, sich unhinterfragt auf KI-Empfehlungen zu verlassen. Die Tendenz zur Algorithmusvermeidung beschreibt die Ablehnung oder das Übergehen von KI-Empfehlungen zugunsten eines menschlichen Urteils. Um dieses Spannungsfeld zu bewältigen, müssen transparente und erklärbare KI-Systeme entwickelt und eine effektive Zusammenarbeit zwischen Menschen und KI gefördert werden. Durch die Berücksichtigung dieser Faktoren und die Stärkung des Vertrauens kann MKI zu einer informierteren Entscheidungsfindung und einer effektiven Nutzung der KI-Funktionen führen KW - Künstliche Intelligenz KW - Künstliche Intelligenz KW - Mensch-KI-Interaktion KW - Vertrauen Y1 - 2024 UR - https://link.springer.com/chapter/10.1007/978-3-658-43816-6_2 U6 - https://doi.org/10.1007/978-3-658-43816-6_2 SP - 17 EP - 31 PB - Springer Fachmedien CY - Wiesbaden ER - TY - CHAP A1 - Smeets, Mario A1 - Rötzel, Peter T1 - The Moderating Role of Relative Performance Information in Reducing Algorithm Aversion In The Adoption Of AI-Based Decision Support Systems in Insolvency Prediction Tasks T2 - 4th ENEAR Conference at Erasmus University Rotterdam N2 - The integration of Artificial Intelligence (AI) into decision-making processes emerges as a pivotal strategy for enhancing organizational performance. The paper delves into the criticality of trust in AI-based Decision Support Systems (DSSs), similar to the trust required for other (Accounting) information systems to integrate them efficiently. We explore the disruptive phenomenon known as "algorithm aversion" - a significant barrier to the trust and acceptance of AI. Although AI recommendations outperform human recommendations in different decision-making fields, there exists a tendency among individuals to underweight AI-based DSSs recommendations relative to those from human decision-makers. This underutilization is attributed to the lack of trust in AI. We conducted a laboratory experiment designed to investigate the role of AI recommendations in a workplace-related task in the field of financial accounting. The study is twofold: firstly, it examines how AI trust mediates and algorithm aversion adversely impacts decision-making performance, while also considering the moderating role of technical competence. Secondly, it investigates the potential of gamification by using means of Relative Performance Information (RPI) as a strategy to mitigate the effects of algorithm aversion. Through this experiment, we provide empirical evidence on methods to enhance decision-making performance in the context of AI recommendations. Additionally, we identify and propose counterstrategies to combat algorithm aversion, thereby facilitating the broader adoption and integration of AI-based DSSs in accounting and auditing settings. This study contributes to the accounting and auditing research community by offering insights into how AI can be more effectively incorporated into decision-making processes, addressing both psychological and technical barriers to its acceptance. KW - artificial intelligence KW - algorithm aversion KW - relative performance information KW - Künstliche Intelligenz KW - Entscheidungsprozess KW - Rechnungslegung KW - Wirtschaftsprüfung Y1 - 2024 VL - 4 IS - 1 SP - 1 EP - 18 ER - TY - CHAP A1 - Smeets, Mario A1 - Rötzel, Peter T1 - The Moderating Role of Non-Monetary Gamification in Reducing Algorithm Aversion in the Adoption of AI-based Decision Support Systems T2 - ECIS - European Conference on Information Systems N2 - Integrating artificial intelligence (AI) into decision-making processes is key to improving organizational performance. However, trust in AI-based decision support systems (DSSs), similar to other information systems, is important for successful integration. A disruptive phenomenon, “algorithm aversion”, can impede AI trust and, thus, acceptance. Although AI recommendations outperform human recommendations in different decision-making fields, individuals underweight recommendations from AI-based DSSs compared to human decision-makers due to a lack of AI trust. We conducted a lab experiment to investigate the role of AI recommendations in workplace-related tasks, first focusing on the mediating effect of AI trust and the negative impact of algorithm aversion on decision-making performance and the moderating effect of technical competence. Second, we analyzed the ability of gamification to reduce this phenomenon. We provide evidence regarding how to enhance decision-making performance when AI recommendations are deployed and identify countermeasures against algorithm aversion to facilitate the adoption of AI-based DSSs. KW - Decision Support Systems KW - Algorithm Aversion KW - Gamification KW - Künstliche Intelligenz KW - Gamification Y1 - 2024 VL - 2024 IS - 1 ER - TY - CHAP A1 - Rötzel, Peter A1 - Bustorff, Naomi A1 - Kokott, Peter T1 - Analysis of the Impact of Recommendations from Intelligent Expert Systems on Personal Trust and Decision-Making Performance KW - Artificial Intelligence KW - Trust KW - Intelligent Expert Systems KW - Künstliche Intelligenz KW - Vertrauen Y1 - 2023 ER - TY - JOUR A1 - Smeets, Mario A1 - Ostendorf, Ralf A1 - Rötzel, Peter T1 - AI and its Opportunities for Decision Making in an Organizational Context: A Systematic Review of the Influencing Factors on the Intention to use AI JF - Die Unternehmung – Swiss Journal of Business Research and Practice N2 - One domain of application of artificial intelligence (AI) is decision support, particularly in management. Although there are already research streams examining the interaction of AI and humans (e.g. the stream on "hybrid intelligence"), there are still numerous open research gaps – for example, a comprehensive overview of which factors favor the intention to use AI is missing. By conducting a systematic literature review, we identify the factors that potentially positively influence AI usage intentions for decision-making processes in organizations. From this, we create a framework that both provides practical implications for the successful use of AI in organizational decision-making processes and delivers further research approaches, for example, on the validity/ usability of proven IS adoption models in the present context. KW - Artificial Intelligence KW - Decision-making KW - Management Control KW - information systems KW - information management KW - Künstliche Intelligenz KW - Entscheidungsfindung KW - Management Y1 - 2021 VL - 2021 IS - OnlineFirst SP - 1 EP - 28 ER -