Recommender systems are ubiquitous and influence the information we consume daily by helping us navigate vast catalogs of information like music databases. However, their linear approach of surfacing content in ranked lists limits their ability to help us grow and understand our personal preferences. In this paper, we study how we can better support users in exploring a novel space, specifically focusing on music genres. Informed by interviews with expert music listeners, we developed TastePaths: an interactive web tool that helps users explore an overview of the genre-space via a graph of connected artists. We conducted a comparative user study with 16 participants where each of them used a personalized version of TastePaths (built with a set of artists the user listens to frequently) and a non-personalized one (based on a set of the most popular artists in a genre). We find that participants employed various strategies to explore the space. Overall, they greatly preferred the personalized version as it helped anchor their exploration and provided recommendations that were more compatible with their personal taste. In addition to that, TastePaths helped participants specify and articulate their interest in the genre and gave them a better understanding of the system’s organization of music. Based on our findings, we discuss opportunities and challenges for incorporating more control and expressive feedback in recommendation systems to help users explore spaces beyond their immediate interests and improve these systems’ underlying algorithms.

In order to support fairness-forward thinking by machine learning (ML) practitioners, fairness researchers have created toolkits that aim to transform state-of-the-art research contributions into easily-accessible APIs. Despite these efforts, recent research indicates a disconnect between the needs of practitioners and the tools offered by fairness research. By engaging 20 ML practitioners in a simulated scenario in which they utilize fairness toolkits to make critical decisions, this work aims to utilize practitioner feedback to inform recommendations for the design and creation of fair ML toolkits. Through the use of survey and interview data, our results indicate that though fair ML toolkits are incredibly impactful on users’ decision-making, there is much to be desired in the design and demonstration of fairness results. To support the future development and evaluation of toolkits, this work offers a rubric that can be used to identify critical components of Fair ML toolkits.

Voice assistants offer users access to an increasing variety of personalized functionalities. Researchers and engineers who build these experiences rely on various signals from users to create the machine learning models powering them. One type of signal is explicit feedback. While collecting explicit user feedback in situ via voice assistants would help improve and inspect the underlying models, from a user perspective it can be disruptive to the overall experience, and the user might not feel compelled to respond. However, careful design can help alleviate the friction in the experience. In this paper, we explore the opportunities and the design space for voice assistant explicit feedback elicitation. First, we present four usage categories of explicit feedback in situ for model evaluation and improvement, derived from interviews with machine learning practitioners. Then, using realistic scenarios generated for each category, we conducted an online study to evaluate multiple voice assistant designs. Our results reveal that when the voice assistant is introduced as a learner or a collaborator, users were more willing to respond to its request for feedback and felt less disruptive. In addition, giving users instructions on how to initiate feedback themselves can reduce the perceived disruptiveness compared to asking users for feedback directly. Based on our findings, we discuss the implications and potential future directions for designing voice assistants to elicit user feedback for personalized voice experiences.

It can be difficult for user researchers to explore how people might interact with interactive systems in everyday contexts; time and space limitations make it hard to be present everywhere that technology is used. Digital music services are one domain where designing for context is important given the myriad places people listen to music. One novel method to help design researchers embed themselves in everyday contexts is through remote-controlled speech agents. This paper describes a practitioner-centered case study of music service interaction researchers using a remote-controlled speech agent, called DJ Bot, to explore people's music interaction in the car and the home. DJ Bot allowed the team to conduct remote user research and contextual inquiry and to quickly explore new interactions. However, challenges using a remote speech-agent arose when adapting DJ Bot from the constrained environment of the car to the unconstrained home environment.

Music streaming services collect listener data to support personalization and discovery of their extensive catalogs. Yet this data is typically used in ways that are not immediately apparent to listeners. We conducted design workshops with ten Spotify listeners to imagine future voice assistant (VA) interactions leveraging logged music data. We provided participants with detailed personal music listening data, such as play-counts and temporal patterns, which grounded their design ideas in their current behaviors. In the interactions participants designed, VAs did not simply speak their data out loud; instead, participants envisioned how data could implicitly support introspection, behavior change, and exploration. We present reflections on how VAs could evolve from voice-activated remote controls to intelligent music coaches and how personal data can be leveraged as a design resource.

Music-streaming platforms offer users a large amount of content for consumption. Finding the right music can be challenging and users often need to search through extensive catalogs provided by these platforms. Prior research has focused on general-domain web search, which is designed to meet a broad range of user goals. Here, we study search in the domain of music, seeking to understand how and why people use search and how they evaluate their search experiences on a music-streaming platform. Over two studies, we conducted semi-structured interviews with 27 participants, asking about their search habits and preferences, and observing their behavior while searching for music. Analysis revealed participants evaluated their search experiences along two dimensions: success and effort. Importantly, how participants perceived success and effort differed by their mindset, or the way they assessed the results of their query. We conclude with recommendations to improve the user experience of music search.

Instant search has become a popular search paradigm in which users are shown a new result page in response to every keystroke triggered. Over recent years, the paradigm has been widely adopted in several domains including personal email search, e-commerce, and music search. However, the topic of evaluation and metrics of such systems has been less explored in the literature thus far. In this work, we describe a mixed methods approach to understanding user expectations and evaluating an instant search system in the context of music search. Our methodology involves conducting a set of user interviews to gain a qualitative understanding of users' behaviors and their expectations. The hypotheses from user research are then extended and verified by a large-scale quantitative analysis of interaction logs. Using music search as a lens, we show that researchers and practitioners can interpret the behavior logs more effectively when accompanied by insights from qualitative research. Further, we also show that user research eliminates the guesswork involved in identifying users signals that estimate user satisfaction. Finally, we demonstrate that metrics identified using our approach are more sensitive than the commonly used click-through rate metric for instant search.

Music listening is a commonplace activity that has transformed as users engage with online streaming platforms. When presented with anytime, anywhere access to a vast catalog of music, users face challenges in searching for what they want to hear. We propose that users who engage in domain-specific search (e.g., music search) have different information-seeking needs than in general search. Using a mixed-method approach that combines a large-scale user survey with behavior data analyses, we describe the construct of search mindset on a leading online streaming music platform and then investigate two types of search mindsets: focused, where a user is looking for one thing in particular, and non-focused, where a user is open to different results. Our results reveal that searches in the music domain are more likely to be focused than non-focused. In addition, users' behavior (e.g., clicks, streams, querying, etc.) on a music search system is influenced by their search mindset. Finally, we propose design implications for music search systems to best support their users.

Gamification, the use of game mechanics in non-gaming applications, has been applied to various systems to encourage desired user behaviors. In this paper, we examine patterns of user activity in an enterprise social network service after the removal of a points-based incentive system. Our results reveal that the removal of the incentive scheme did reduce overall participation via contribution within the SNS. We also describe the strategies by point leaders and observe that users geographically distant from headquarters tended to comment on profiles outside of their home country. Finally, we describe the implications of the removal of extrinsic rewards, such as points and badges, on social software systems, particularly those deployed within an enterprise.

For large global enterprises, providing adequate resources for organizational acculturation, the process in which employees learn about an organization's culture, remains a challenge. We present results from a survey of 802 users from an enterprise social networking site that identifies two groups of employees (new to the company and geographically distant from headquarters) that perceive higher benefit from using a SNS to learn about the organization's values and beliefs. In addition, we observe regional differences in viewing behaviors between two groups of new employees. These results suggest that a SNS can also potentially contribute to the information-seeking and sense-making activities that underlie organization acculturation.

When experts participate in collaborative systems, tension may arise between them and novice contributors. In particular, when experts perceive novices as a bother or a threat, the experts may express territoriality: behaviors communicating ownership of a target of interest. In this paper, we describe the results of a user study of a mobile social tagging system deployed within a museum gallery to a group of novices and experts collaboratively tagging part of the collection. We observed that experts express greater feelings of ownership towards their contributions to the system and the museum in general. Experts were more likely than novices to participate at higher rates and to negatively evaluate contributions made by others. We suggest a number of design strategies to balance experts' expressions of territoriality so as to motivate their participation while discouraging exclusionary behaviors.

In this poster, we describe the current findings of a work-in-progress that seeks to understand the normative climate that arises within user-generated media communities when contributions are interpreted as stolen or otherwise misappropriated. We outline our data collection on the photosharing service flickr.com and then briefly discuss the emergent categories of user response to perceived unauthorized reuse that appear within our sample.

Territoriality, the expression of ownership towards an object, can emerge when social actors occupy a shared social space. In the case of Wikipedia, the prevailing cultural norm is one that warns against ownership of one's work. However, we observe the emergence of territoriality in online space with respect to a subset of articles that have been tagged with the Maintained template through a qualitative study of 15 editors who have self-designated as Maintainers. Our participants communicated ownership, demarcated boundaries and asserted their control over artifacts for the sake of quality by appropriating existing features of Wikipedia. We then suggest design strategies to support these behaviors in the proper context within collaborative authoring systems more generally.

In this paper, we focus on the role that photo viewing plays within a large distributed enterprise. We describe the results of an analysis of users' viewing behavior through log activity and semi-structured interviews with respect to a photo sharing application embedded within an internal social networking site. Specifically, we investigate how these forms of expression can assist in the transmission of the norms and values associated with the culture of the organization through impression formation. We conclude by discussing how photos might act as a resource for newcomers to learn about the various aspects of the organizational culture and offer design suggestions for photo viewing systems within organizations.

Territoriality, the expression of ownership towards an object, can emerge when social actors occupy a shared social space. In my research, I extend the study of territoriality beyond previous work in physical space in two key ways: 1) the object in question is virtual and 2) the social context is an online community engaged in collaborative activity. To do this, I observe the emergence of characteristic territorial behaviors (e.g. marking, control, defense) within collaborative authoring and social tagging. My dissertation then uses these observations to construct a theoretical framework for online territoriality to provide researchers and designers of groupware with guidelines with which to encourage ownership expression when appropriate.

The interplay between arts and HCI has become increasingly commonplace in the past years, offering new opportunities for approaching interaction, but also raising challenges in integrating methods and insights from across a great disciplinary divide. In this paper, we examine the ways Situationist art practice has been used as an inspiration for HCI design. We argue that methods from Situationist art practice have often been picked up without regard for their underlying sensibility: reflection and improvisation in an activist socio-political context. We describe an experiment in incorporating Situationist sensibility in design and use it to elucidate the challenges that face HCI in truly integrating the arts.

Social tagging systems provide users with the opportunity to employ tags in a communicative manner. To explore the use of tags for communication in these systems, we report results from 33 user interviews and employ the concept of social roles to describe audience-oriented tagging, including roles of community-seeker, community-builder, evangelist, publisher, and team-leader. These roles contribute to our understanding of the motivations and rationales behind social tagging in an international company, and suggest new features and services to support social software in the enterprise.

Social psychology has demonstrated that lying is an important, and frequent, part of everyday social interactions. As communication technologies become more ubiquitous in our daily interactions, an important question for developers is to determine how the design of these technologies affects lying behavior. The present research reports the results of a diary study, in which participants recorded all of their social interactions and lies for seven days. The data reveal that participants lied most on the telephone and least in email, and that lying rates in face-to-face and instant messaging interactions were approximately equal. This pattern of results suggests that the design features of communication technologies (e.g., synchronicity, recordability, and copresence) affect lying behavior in important ways, and that these features must be considered by both designers and users when issues of deception and trust arise. The implications for designing applications that increase, decrease or detect deception are discussed.