Ngo, Phuong Thao; Kunkel, Johannes; Ziegler, Jürgen:
Exploring Mental Models for Transparent and Controllable Recommender Systems : A Qualitative Study
In: UMAP 2020 - Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization - UMAP 2020; Genoa, Italy; 14 - 17 July 2020 - New York: Association for Computing Machinery (ACM), 2020, pp. 183 - 191
2020book article/chapter in ProceedingsOA Gold
Computer ScienceFaculty of Engineering » Computer Science and Applied Cognitive Science » Computer Science » Interactive Systems
Title in English:
Exploring Mental Models for Transparent and Controllable Recommender Systems : A Qualitative Study
Author:
Ngo, Phuong ThaoUDE
LSF ID
60158
ORCID
0000-0001-5147-8272ORCID iD
Other
connected with university
;
Kunkel, JohannesUDE
LSF ID
57574
Other
connected with university
;
Ziegler, JürgenUDE
GND
1015876811
LSF ID
3881
ORCID
0000-0001-9603-5272ORCID iD
Other
connected with university
Open Access?:
OA Gold
Scopus ID
Language of text:
English
Keyword, Topic:
grounded theory ; mental models ; recommender systems ; think aloud ; transparent AI

Abstract in English:

While online content is personalized to an increasing degree, eg. using recommender systems (RS), the rationale behind personalization and how users can adjust it typically remains opaque. This was often observed to have negative effects on the user experience and perceived quality of RS. As a result, research increasingly has taken user-centric aspects such as transparency and control of a RS into account, when assessing its quality. However, we argue that too little of this research has investigated the users' perception and understanding of RS in their entirety. In this paper, we explore the users' mental models of RS. More specifically, we followed the qualitative grounded theory methodology and conducted 10 semi-structured face-to-face interviews with typical and regular Netflix users. During interviews participants expressed high levels of uncertainty and confusion about the RS in Netflix. Consequently, we found a broad range of different mental models. Nevertheless, we also identified a general structure underlying all of these models, consisting of four steps: data acquisition, inference of user profile, comparison of user profiles or items, and generation of recommendations. Based on our findings, we discuss implications to design more transparent, controllable, and user friendly RS in the future.