Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradigm based on a guided interaction pattern aimed at both eliciting the users’ preferences and heading them toward effective recourse interventions. In a fictional task of money lending, we compare this approach with an exploratory interaction pattern based on a combination of alternative plans and the possibility of freely changing the configurations by the users themselves. Our results suggest that users may recognize that the guided interaction paradigm improves efficiency. However, they also feel less freedom to experiment with "what-if" scenarios. Nevertheless, the time spent on the purely exploratory interface tends to be perceived as a lack of efficiency, which reduces attractiveness, perspicuity, and dependability. Conversely, for the guided interface, more time on the interface seems to increase its attractiveness, perspicuity, and dependability while not impacting the perceived efficiency. That might suggest that this type of interfaces should combine these two approaches by trying to support exploratory behavior while gently pushing toward a guided effective solution.

Preference Elicitation in Interactive and User-centered Algorithmic Recourse: an Initial Exploration / Esfahani, Seyedehdelaram; De Toni, Giovanni; Lepri, Bruno; Passerini, Andrea; Tentori, Katya; Zancanaro, Massimo. - (2024), pp. 249-254. (Intervento presentato al convegno 32nd Conference on User Modeling, Adaptation and Personalization, UMAP 2024 tenutosi a Cagliari, Italy nel 1-4 Luglio 2024) [10.1145/3627043.3659556].

Preference Elicitation in Interactive and User-centered Algorithmic Recourse: an Initial Exploration

De Toni, Giovanni;Lepri, Bruno;Passerini, Andrea;Tentori, Katya;Zancanaro, Massimo
2024-01-01

Abstract

Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradigm based on a guided interaction pattern aimed at both eliciting the users’ preferences and heading them toward effective recourse interventions. In a fictional task of money lending, we compare this approach with an exploratory interaction pattern based on a combination of alternative plans and the possibility of freely changing the configurations by the users themselves. Our results suggest that users may recognize that the guided interaction paradigm improves efficiency. However, they also feel less freedom to experiment with "what-if" scenarios. Nevertheless, the time spent on the purely exploratory interface tends to be perceived as a lack of efficiency, which reduces attractiveness, perspicuity, and dependability. Conversely, for the guided interface, more time on the interface seems to increase its attractiveness, perspicuity, and dependability while not impacting the perceived efficiency. That might suggest that this type of interfaces should combine these two approaches by trying to support exploratory behavior while gently pushing toward a guided effective solution.
2024
Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and PersonalizationJune UMAP '24
New York
Association for Computing Machinery, Inc
979-8-4007-0433-8
Esfahani, Seyedehdelaram; De Toni, Giovanni; Lepri, Bruno; Passerini, Andrea; Tentori, Katya; Zancanaro, Massimo
Preference Elicitation in Interactive and User-centered Algorithmic Recourse: an Initial Exploration / Esfahani, Seyedehdelaram; De Toni, Giovanni; Lepri, Bruno; Passerini, Andrea; Tentori, Katya; Zancanaro, Massimo. - (2024), pp. 249-254. (Intervento presentato al convegno 32nd Conference on User Modeling, Adaptation and Personalization, UMAP 2024 tenutosi a Cagliari, Italy nel 1-4 Luglio 2024) [10.1145/3627043.3659556].
File in questo prodotto:
File Dimensione Formato  
Esfahani et al. - 2024 - Preference Elicitation in Interactive and User-cen.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.97 MB
Formato Adobe PDF
1.97 MB Adobe PDF Visualizza/Apri
Esfahani et al. 2024 - IUI PREPRIN.pdf

accesso aperto

Tipologia: Pre-print non referato (Non-refereed preprint)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.98 MB
Formato Adobe PDF
1.98 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/414551
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact