Artificial Intelligence (AI) supports many of our everyday activities and decisions. However, personalized algorithmic recommendations often produce adverse experiences due to a lack of awareness, control, or transparency. While research has directed solutions on graphical user interfaces (GUIs), there are no explorations of Tangible User Interfaces (TUIs) to improve the experience with such systems, despite the valid existing academic arguments in favor of this exploration. Therefore, centering on transparency and control, we analyzed how 18 users of movie recommender systems perceived four different TUIs using individual co-design sessions and post-interview questionnaires. Through thematic analysis, we identified seven design considerations while designing TUIs to interact with algorithmic movie recommender systems: (1) Distinctions between TUIs and GUIs; (2) TUIs replacing predominant interfaces; (3) Preference for single-device TUIs; (4) The relevance of granular control for TUIs; (5) Apparent transparency limitations of TUIs; (6) TUIs and algorithmic social computing; and (7) Overview of specific design choices, including advantages and disadvantages of soft, hard, rounded, cubic, and humanoid interfaces. These findings inspired Recffy: the first functional TUI designed to enhance awareness and control in personalized movie recommendations. Based on this study, we propose the concept of Tangible Algorithms: TUIs dedicated to enhancing the interaction of algorithmic systems and their profiling processes or decisions in a specific context. Furthermore, we describe the relevance of tangible algorithms and design guidelines to promote them in diverse AI contexts. Finally, we invite the HCI and CSCW community to continue exploring tangible algorithms to address the interaction with algorithmic systems, including the collaborative and social computing dynamics they can promote in diverse AI contexts.

Systems involving artificial intelligence (AI) are protagonists in many everyday activities. Moreover, designers are increasingly implementing these systems for groups of users in various social and cooperative domains. Unfortunately, research on personalized recommendation systems often reports negative experiences due to a lack of diversity, control, or transparency. Providing a meta-analysis of the interaction design strategies for group recommendation systems (GRS) offers designers and practitioners a departure to address these issues and imagine new interaction possibilities for this context. Therefore, we systematically reviewed the ACM, IEEE, and Scopus digital libraries to identify GRS interface designs, resulting in a final corpus of 142 academic papers. After a systematic coding process, we used descriptive statistics and thematic analysis to uncover the current state of the art regarding interaction design strategies for GRS in six areas: (1) application domains; (2) devices chosen to implement the systems; (3) prototype fidelity; (4) strategies for profile transparency, justification, control, and diversity; (5) strategies for group formation and final group consensus; and, (6) evaluation methods applied in user studies during the design process. Based on our findings, we present an exhaustive typology of interaction design strategies for GRS and a set of research opportunities to foster human-centered interfaces for personalized recommendations in cooperative and social computing contexts.

Algorithmic systems that recommend content often lack transparency about how they come to their suggestions. One area in which recommender systems are increasingly prevalent is online news distribution. In this paper, we explore how a lack of transparency of (news) recommenders can be tackled by involving users in the design of interface elements. In the context of automated decision-making, legislative frameworks such as the GDPR in Europe introduce a specific conception of transparency, granting 'data subjects' specific rights and imposing obligations on service providers. An important related question is how people using personalized recommender systems relate to the issue of transparency, not as legal data subjects but as users. This paper builds upon a two-phase study on how users conceive of transparency and related issues in the context of algorithmic news recommenders. We organized co-design workshops to elicit participants' 'algorithmic imaginaries' and invited them to ideate interface elements for increased transparency. This revealed the importance of combining legible transparency features with features that increase user control. We then conducted a qualitative evaluation of mock-up prototypes to investigate users' preferences and concerns when dealing with design features to increase transparency and control. Our investigation illustrates how users' expectations and impressions of news recommenders are closely related to their news reading practices. On a broader level, we show how transparency and control are conceptually intertwined. Transparency without control leaves users frustrated. Conversely, without a basic level of transparency into how a system works, users remain unsure of the impact of controls.

Recommender algorithms play an active role in many everyday activities. However, personalized recommendations often produce negative experiences due to a lack of awareness, control, or transparency. Allowing users to materialize their algorithmic imaginaries exposes how they experience, perceive, and imagine recommender algorithms. Moreover, it can unearth novel and previously unattended design opportunities for tangible interactions with algorithms. Therefore, we explored how 15 users of a famous movie recommender system materialized tangible designs to reflect and discuss their algorithmic imaginaries during co-design workshops and interviews. Using thematic analysis, we identified two forms of algorithmic imaginaries that can inspire tangible interactions with recommender algorithms: metaphoric and datafied representations. Complementary themes exposed the influence of contextual factors and diverse negative attitudes towards personalized movie recommendations. Based on these findings, we suggest design opportunities and suggestions for improving the algorithmic experience of movie recommendations and similar systems through tangible user interfaces.

User beliefs about algorithmic systems are constantly co-produced through user interaction and the complex socio-technical systems that generate recommendations. Identifying these beliefs is crucial because they influence how users interact with recommendation algorithms. With no prior work on user beliefs of algorithmic video recommendations, practitioners lack relevant knowledge to improve the user experience of such systems. To address this problem, we conducted semi-structured interviews with middle-aged YouTube video consumers to analyze their user beliefs about the video recommendation system. Our analysis revealed different factors that users believe influence their recommendations. Based on these factors, we identified four groups of user beliefs: Previous Actions, Social Media, Recommender System, and Company Policy. Additionally, we propose a framework to distinguish the four main actors that users believe influence their video recommendations: the current user, other users, the algorithm, and the organization. This framework provides a new lens to explore design suggestions based on the agency of these four actors. It also exposes a novel aspect previously unexplored: the effect of corporate decisions on the interaction with algorithmic recommendations. While we found that users are aware of the existence of the recommendation system on YouTube, we show that their understanding of this system is limited.

Recommender algorithms deal with most of our contemporary culture consumption. Algorithmic Experience (AX) emerges in HCI to guide users' experience with algorithms. To the best of our knowledge, previous work on recommender systems does not consider tangible interfaces to support positive AX and better algorithmic awareness. The ongoing research proposes to expand the design space for the current AX debate by designing an embodied interface suited for movie recommender algorithms.

Algorithms influence most of our daily activities, decisions, and they guide our behaviors. It has been argued that algorithms even have a direct impact on democratic societies. Human - Computer Interaction research needs to develop analytical tools for describing the interaction with, and experience of algorithms. Based on user participatory workshops focused on scrutinizing Facebook's newsfeed, an algorithm-influenced social media, we propose the concept of Algorithmic Experience (AX) as an analytic framing for making the interaction with and experience of algorithms explicit. Connecting it to design, we articulate five functional categories of AX that are particularly important to cater for in social media: profiling transparency and management, algorithmic awareness and control, and selective algorithmic memory.