Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms

Szczuka JM, Horstmann AC, Szymczyk N, Strathmann C, Artelt A, Mavrina L, Krämer N (2024)
In: NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction. Association for Computing Machinery (Ed); New York, USA.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Szczuka, Jessica M.; Horstmann, Aike C.; Szymczyk, Natalia; Strathmann, Clara; Artelt, AndréUniBi ; Mavrina, LinaUniBi ; Krämer, Nicole
herausgebende Körperschaft
Association for Computing Machinery
Abstract / Bemerkung
AI-based systems become ubiquitous but stay opaque. To promote informed usage, explanations of how systems compute outcomes emerged as a promising strategy (XAI). Moreover, there is a trend of equipping technologies with human-like features (e.g., natural language, social roles) to enhance the system's person-likeness, thereby influencing users' understanding and trust. The present empirical study (N = 762) investigates the effects and interplay of explanation types and person-likeness on understanding of and trust in AI-systems. It is designed as 2 (contrastive 'why not' explanations vs. comparative 'why' explanation) x 2 (self-referencing vs. neutral formulation) between-subject study with a no explanation-baseline condition. Results demonstrate positive effects of explanations on people's understanding, whereby contrastive explanations – despite being perceived as more complex – led to significantly higher factual understanding compared to the comparative explanations. Person-likeness had no effect on trust or understanding which challenges current trends of enhancing human-like features of technologies.
Erscheinungsjahr
2024
Titel des Konferenzbandes
NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction
Art.-Nr.
18
Konferenz
NordCHI '24: Nordic Conference on Human-Computer Interaction
Konferenzort
Uppsala, Sweden
Konferenzdatum
2024-10-13 – 2024-10-16
Page URI
https://pub.uni-bielefeld.de/record/2993831

Zitieren

Szczuka JM, Horstmann AC, Szymczyk N, et al. Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms. In: Association for Computing Machinery, ed. NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction. New York, USA; 2024.
Szczuka, J. M., Horstmann, A. C., Szymczyk, N., Strathmann, C., Artelt, A., Mavrina, L., & Krämer, N. (2024). Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms. In Association for Computing Machinery (Ed.), NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction New York, USA. https://doi.org/10.1145/3679318.368535
Szczuka, Jessica M., Horstmann, Aike C., Szymczyk, Natalia, Strathmann, Clara, Artelt, André, Mavrina, Lina, and Krämer, Nicole. 2024. “Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms”. In NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction, ed. Association for Computing Machinery. New York, USA: 18.
Szczuka, J. M., Horstmann, A. C., Szymczyk, N., Strathmann, C., Artelt, A., Mavrina, L., and Krämer, N. (2024). “Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms” in NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction, Association for Computing Machinery ed. (New York, USA).
Szczuka, J.M., et al., 2024. Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms. In Association for Computing Machinery, ed. NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction. New York, USA.
J.M. Szczuka, et al., “Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms”, NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction, Association for Computing Machinery, ed., New York, USA: 2024.
Szczuka, J.M., Horstmann, A.C., Szymczyk, N., Strathmann, C., Artelt, A., Mavrina, L., Krämer, N.: Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms. In: Association for Computing Machinery (ed.) NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction. New York, USA (2024).
Szczuka, Jessica M., Horstmann, Aike C., Szymczyk, Natalia, Strathmann, Clara, Artelt, André, Mavrina, Lina, and Krämer, Nicole. “Let Me Explain What I Did or What I Would Have Done: An Empirical Study on the Effects of Explanations and Person-Likeness on Trust in and Understanding of Algorithms”. NordiCHI '24: Proceedings of the 13th Nordic Conference on Human-Computer Interaction. Ed. Association for Computing Machinery. New York, USA, 2024.

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar