Hellmann, Marco; Hernandez Bocanegra, Diana; Ziegler, Jürgen:
Development of an Instrument for Measuring Users’ Perception of Transparency in Recommender Systems
In: Workshops at the International Conference on Intelligent User Interfaces (IUI) 2022 : Proceedings of the IUI 2022 Workshops: APEx-UI, HAI-GEN, HEALTHI, HUMANIZE, TExSS, SOCIALIZE / Smith-Renner, Alison; Amir, Ofra (Hrsg.). - Conference on Intelligent User Interfaces (IUI 2022), 21-22 March 2022, Helsinki - Aachen: RWTH Aachen, 2022 - (CEUR Workshop Proceedings ; 3124), S. 156 - 165
2022Buchaufsatz/Kapitel in TagungsbandOA Platin
ElektrotechnikFakultät für Ingenieurwissenschaften » Informatik und Angewandte Kognitionswissenschaft
Damit verbunden: 1 Publikation(en)
Titel in Englisch:
Development of an Instrument for Measuring Users’ Perception of Transparency in Recommender Systems
Autor*in:
Hellmann, MarcoUDE
LSF ID
58801
Sonstiges
der Hochschule zugeordnete*r Autor*in
;
Hernandez Bocanegra, DianaUDE
GND
1256307963
LSF ID
60092
ORCID
0000-0002-1773-2633ORCID iD
Sonstiges
der Hochschule zugeordnete*r Autor*in
;
Ziegler, JürgenUDE
GND
1015876811
GND
1077664516
LSF ID
3881
ORCID
0000-0001-9603-5272ORCID iD
Sonstiges
der Hochschule zugeordnete*r Autor*in
Open Access?:
OA Platin
DuEPublico 2 ID
Sprache des Textes:
Englisch
Schlagwort, Thema:
Recommender systems

Abstract in Englisch:

Transparency is increasingly seen as a critical requirement for achieving the goal of human-centered AI systems in general and also, specifically, recommender systems (RS). However, defining and operationalizing the concept is still difficult, due to its multi-faceted nature. Currently, there are hardly any measurement instruments to adequately assess the perceived transparency of RS in user studies. Thus, we present the development of a measurement instrument that aims at capturing perceived transparency as a multidimensional construct. The results of our validation show that transparency can be distinguished with respect to input (what data does the system use?), functionality (how and why is an item recommended?), output (why and how well does an item fit one’s preferences?), and interaction (what needs to be changed for a different prediction?). The study is intended as a first iteration in the development of a reliable and fully validated measurement tool for assessing transparency in RS.