Product returns are an increasing environmental problem, as an estimated 25% of returned products end up as landfill [10]. Returns are expensive for retailers as well, and it is estimated that 15-40% of all online purchases are returned [34]. The problem could be mitigated by identifying issues with a product that are likely to lead to its return, before many have sold. Understanding and predicting return reasons can help identify manufacturing defects, misleading information in the product description or reviews, issues with a seller or shipping company, and customers who are habitual returners. While there has been much work to identify and predict return volume, little attention has been given to the reasons for the return. In this paper we explore how customer reviews could be used as signals to identify return reasons. We developed a multi-class classifier to predict return reasons, with a fine-tuned BERT-based model to encode customer review text as features. The classifier with customer review text yields an increase of more than 20% average precision over the baseline classifier with no reviews text. We also showed that we can use aggregated review information to predict product return in case the customer returning the product did not write a review. Lastly we show that reviews can be used to identify nuanced return reasons beyond what the customer indicated.

Immersive technologies such as virtual reality (VR) and head-mounted displays (HMD) have seen increased adoption in recent years. In this work, we study two factors that influence users' experience when shopping in VR through voice queries: (1) context alignment of the search environment and (2) the level of detail on the Search Engine Results Page (SERP). To this end, we developed a search system for VR and conducted a within-subject exploratory study (N=18) to understand the impact of the two experimental conditions. Our results suggest that both context alignment and SERP are important factors for information-seeking in VR, which present unique opportunities and challenges. More specifically, based on our findings, we suggest that search systems for VR must be able to: (1) provide cues for information-seeking in both the VR environment and SERP, (2) distribute attention between the VR environment and the search interface, (3) reduce distractions in the VR environment and (4) provide a ''sense of control'' to search in the VR environment.

Data-driven AI systems are increasingly used to augment human decision-making in complex, social contexts, such as social work or legal practice. Yet, most existing design knowledge regarding how to best support AI-augmented decision-making comes from studies in comparatively well-defined settings. In this paper, we present findings from design interviews with 12 social workers who use an algorithmic decision support tool (ADS) to assist their day-to-day child maltreatment screening decisions. We generated a range of design concepts, each envisioning different ways of redesigning or augmenting the ADS interface. Overall, workers desired ways to understand the risk score and incorporate contextual knowledge, which move beyond existing notions of AI interpretability. Conversations around our design concepts also surfaced more fundamental concerns around the assumptions underlying statistical prediction, such as inference based on similar historical cases and statistical notions of uncertainty. Based on our findings, we discuss how ADS may be better designed to support the roles of human decision-makers in social decision-making contexts.

Machine learning tools have been deployed in various contexts to support human decision-making, in the hope that human-algorithm collaboration can improve decision quality. However, the question of whether such collaborations reduce or exacerbate biases in decision-making remains underexplored. In this work, we conducted a mixed-methods study, analyzing child welfare call screen workers’ decision-making over a span of four years, and interviewing them on how they incorporate algorithmic predictions into their decision-making process. Our data analysis shows that, compared to the algorithm alone, workers reduced the disparity in screen-in rate between Black and white children from 20% to 9%. Our qualitative data show that workers achieved this by making holistic risk assessments and adjusting for the algorithm’s limitations. Our analyses also show more nuanced results about how human-algorithm collaboration affects prediction accuracy, and how to measure these effects. These results shed light on potential mechanisms for improving human-algorithm collaboration in high-risk decision-making contexts.

AI-based decision support tools (ADS) are increasingly used to augment human decision-making in high-stakes, social contexts. As public sector agencies begin to adopt ADS, it is critical that we understand workers’ experiences with these systems in practice. In this paper, we present findings from a series of interviews and contextual inquiries at a child welfare agency, to understand how they currently make AI-assisted child maltreatment screening decisions. Overall, we observe how workers’ reliance upon the ADS is guided by (1) their knowledge of rich, contextual information beyond what the AI model captures, (2) their beliefs about the ADS’s capabilities and limitations relative to their own, (3) organizational pressures and incentives around the use of the ADS, and (4) awareness of misalignments between algorithmic predictions and their own decision-making objectives. Drawing upon these findings, we discuss design implications towards supporting more effective human-AI decision-making.

The computational capabilities of recent mobile devices enable the processing of natural features for Augmented Reality (AR), but the scalability is still limited by the devices' computation power and available resources. In this paper, we propose EdgeXAR, a mobile AR framework that utilizes the advantages of edge computing through task offloading to support flexible camera-based AR interaction. We propose a hybrid tracking system for mobile devices that provides lightweight tracking with 6 Degrees of Freedom and hides the offloading latency from users' perception. A practical, reliable and unreliable communication mechanism is used to achieve fast response and consistency of crucial information. We also propose a multi-object image retrieval pipeline that executes fast and accurate image recognition tasks on the cloud and edge servers. Extensive experiments are carried out to evaluate the performance of EdgeXAR by building mobile AR apps upon it. Regarding the Quality of Experience (QoE), the mobile AR apps powered by EdgeXAR framework run on average at the speed of 30 frames per second with precise tracking of only 1-2 pixel errors and accurate image recognition of at least 97% accuracy. As compared to Vuforia, one of the leading commercial AR frameworks, EdgeXAR transmits 87% less data while providing a stable 30FPS performance and reducing the offloading latency by 50 to 70% depending on the transmission medium. Our work facilitates the large-scale deployment of AR as the next generation of ubiquitous interfaces.

Recent work in fair machine learning has proposed dozens of technical definitions of algorithmic fairness and methods for enforcing these definitions. However, we still lack an understanding of how to develop machine learning systems with fairness criteria that reflect relevant stakeholders’ nuanced viewpoints in real-world contexts. To address this gap, we propose a framework for eliciting stakeholders’ subjective fairness notions. Combining a user interface that allows stakeholders to examine the data and the algorithm’s predictions with an interview protocol to probe stakeholders’ thoughts while they are interacting with the interface, we can identify stakeholders’ fairness beliefs and principles. We conduct a user study to evaluate our framework in the setting of a child maltreatment predictive system. Our evaluations show that the framework allows stakeholders to comprehensively convey their fairness viewpoints. We also discuss how our results can inform the design of predictive systems.

Increasingly, algorithms are used to make important decisions across society. However, these algorithms are usually poorly understood, which can reduce transparency and evoke negative emotions. In this research, we seek to learn design principles for explanation interfaces that communicate how decision-making algorithms work, in order to help organizations explain their decisions to stakeholders, or to support users' "right to explanation". We conducted an online experiment where 199 participants used different explanation interfaces to understand an algorithm for making university admissions decisions. We measured users' objective and self-reported understanding of the algorithm. Our results show that both interactive explanations and "white-box" explanations (i.e. that show the inner workings of an algorithm) can improve users' comprehension. Although the interactive approach is more effective at improving comprehension, it comes with a trade-off of taking more time. Surprisingly, we also find that users' trust in algorithmic decisions is not affected by the explanation interface or their level of comprehension of the algorithm.

Group projects are an essential component of teaching user interface (UI) design. We identified six challenges in transferring traditional group projects into the context of Massive Open Online Courses: managing dropout, avoiding free-riding, appropriate scaffolding, cultural and time zone differences, and establishing common ground. We present a case study of the design of a group project for a UI Design MOOC, in which we implemented technical tools and social structures to cope with the above challenges. Based on survey analysis, interviews, and team chat data from the students over a six-month period, we found that our socio-technical design addressed many of the obstacles that MOOC learners encountered during remote collaboration. We translate our findings into design implications for better group learning experiences at scale.

Online platforms provide new channels for people in need to seek help from friends and strangers. However, individuals often encounter psychological barriers that deter them from asking for help. For example, people might have different concerns about asking for help, including acknowledging incompetence, bothering others, and accruing social debt. These perceived social costs limit the potential benefits of help solicitations. In this study, we attempt to investigate whether anonymity (posting a question anonymously), ephemerality (allowing questions to be visible for only a short period), and system routing (having the system handle the question routing) could reduce social costs in a typical online help-seeking behavior-question asking. We built a platform to support these three features and conducted a controlled within-subjects experiment to test their effects on the social costs of posting questions. Results suggest that the presence of anonymity, ephemerality, and system routing reduce social costs. Further, we find that employing anonymity and system routing features did not lower the quality and quantity of answers to the questions in our system.

Understanding team communication and collaboration patterns is critical for improving work efficiency in organizations. This paper presents an interactive visualization system, T-Cal, that supports the analysis of conversation data from modern team messaging platforms (e.g., Slack). T-Cal employs a user-familiar visual interface, a calendar, to enable seamless multi-scale browsing of data from different perspectives. T-Cal also incorporates a number of analytical techniques for disentangling interleaving conversations, extracting keywords, and estimating sentiment. The design of T-Cal is based on an iterative user-centered design process including interview studies, requirements gathering, initial prototypes demonstration, and evaluation with domain users. The resulting two case studies indicate the effectiveness and usefulness of T-Cal in real-world applications, including daily conversations within an industry research lab and student group chats in a MOOC.

Team project, which emphasizes collaborative learning in a project-based context, is one of the most commonly-used teaching and learning methods in higher education classrooms, but is not well-supported on existing Massive Open Online Course (MOOC) platforms. In this paper, we present ProjectLens, a MOOC supplement tool that supports team projects building and collaborative learning on MOOC platforms like Coursera and edX. In addition, ProjectLens is a research tool that provides opportunities to conduct large-scale field experiments to study how different factors influence the effectiveness of collaborative learning. We illustrate how ProjectLens can achieve these two goals in a case example.

The sharing economy has quickly become a very prominent subject of research in the broader computing literature and the in human--computer interaction (HCI) literature more specifically. When other computing research areas have experienced similarly rapid growth (e.g. human computation, eco-feedback technology), early stage literature reviews have proved useful and influential by identifying trends and gaps in the literature of interest and by providing key directions for short- and long-term future work. In this paper, we seek to provide the same benefits with respect to computing research on the sharing economy. Specifically, following the suggested approach of prior computing literature reviews, we conducted a systematic review of sharing economy articles published in the Association for Computing Machinery Digital Library to investigate the state of sharing economy research in computing. We performed this review with two simultaneous foci: a broad focus toward the computing literature more generally and a narrow focus specifically on HCI literature. We collected a total of 112 sharing economy articles published between 2008 and 2017 and through our analysis of these papers, we make two core contributions: (1) an understanding of the computing community's contributions to our knowledge about the sharing economy, and specifically the role of the HCI community in these contributions (i.e. what has been done ) and (2) a discussion of under-explored and unexplored aspects of the sharing economy that can serve as a partial research agenda moving forward (i.e. what is next to do ).

We describe a new set of interaction techniques that allow users to interact with physical objects through augmented reality (AR). Previously, to operate a smart device, physical touch is generally needed and a graphical interface is normally involved. These become limitations and prevent the user from operating a device out of reach or operating multiple devices at once. Ubii (Ubiquitous interface and interaction) is an integrated interface system that connects a network of smart devices together, and allows users to interact with the physical objects using hand gestures. The user wears a smart glass which displays the user interface in an augmented reality view. Hand gestures are captured by the smart glass, and upon recognizing the right gesture input, Ubii will communicate with the connected smart devices to complete the designated operations. Ubii supports common inter-device operations such as file transfer, printing, projecting, as well as device pairing. To improve the overall performance of the system, we implement computation offloading to perform the image processing computation. Our user test shows that Ubii is easy to use and more intuitive than traditional user interfaces. Ubii shortens the operation time on various tasks involving operating physical devices. The novel interaction paradigm attains a seamless interaction between the physical and digital worlds.