While social media feed rankings are primarily driven by engagement signals rather than any explicit value system, the resulting algorithmic feeds are not value-neutral: engagement may prioritize specific individualistic values. This paper presents an approach for social media feed value alignment. We adopt Schwartz's theory of Basic Human Values -- a broad set of human values that articulates complementary and opposing values forming the building blocks of many cultures -- and we implement an algorithmic approach that models and then ranks feeds by expressions of Schwartz's values in social media posts. Our approach enables controls where users can express weights on their desired values, combining these weights and post value expressions into a ranking that respects users' articulated trade-offs. Through controlled experiments (N=141 and N=250), we demonstrate that users can use these controls to architect feeds reflecting their desired values. Across users, value-ranked feeds align with personal values, diverging substantially from existing engagement-driven feeds.

While generative AI tools are increasingly adopted for creative and analytical tasks, their role in interpretive practices, where meaning is subjective, plural, and non-causal, remains poorly understood. This paper examines AI-assisted tarot reading, a divinatory practice in which users pose a query, draw cards through a randomized process, and ask AI systems to interpret the resulting symbols. Drawing on interviews with tarot practitioners and Hartmut Rosa’s Theory of Resonance, we investigate how users seek, negotiate, and evaluate resonant interpretations in a context where no causal relationship exists between the query and the data being interpreted. We identify distinct ways practitioners incorporate AI into their interpretive workflows, including using AI to navigate uncertainty and self-doubt, explore alternative perspectives, and streamline or extend existing divinatory practices. Based on these findings, we offer design recommendations for AI systems that support interpretive meaning-making without collapsing ambiguity or foreclosing user agency.

Centralized content moderation paradigm both falls short and overreaches: 1) it fails to account for the subjective nature of harm, and 2) it acts with blunt suppression in response to content deemed harmful, even when such content can be salvaged. We first investigate this through formative interviews, documenting how seemingly benign content becomes harmful due to individual life experiences. Based on these insights, we developed DIY-MOD, a browser extension that operationalizes a new paradigm: personalized content transformation. Operating on a user’s own definition of harm, DIY-MOD transforms sensitive elements within content in real-time instead of suppressing the content itself. The system selects the most appropriate transformation for a piece of content from a diverse palette—from obfuscation to artistic stylizing—to match the user’s specific needs while preserving the content’s informational value. Our two user studies demonstrate that this approach increases users’ sense of agency and safety, enabling them to engage with content and communities they previously needed to avoid.

The status-quo of misinformation moderation is a central authority, usually social platforms, deciding what content constitutes misinformation and how it should be handled. However, to preserve users’ autonomy, researchers have explored democratized misinformation moderation. One proposition is to enable users to assess content accuracy and specify whose assessments they trust. We explore how these affordances can be provided on the web, without cooperation from the platforms where users consume content. We present a browser extension that empowers users to assess the accuracy of any content on the web and shows the user assessments from their trusted sources in-situ. Through a two-week user study, we report on how users perceive such a tool, the kind of content users want to assess, and the rationales they use in their assessments. We identify implications for designing tools that enable users to moderate content for themselves with the help of those they trust.

This work aims to explore how human assessments and AI predictions can be combined to identify misinformation on social media. To do so, we design a personalized AI which iteratively takes as training data a single user’s assessment of content and predicts how the same user would assess other content. We conduct a user study in which participants interact with a personalized AI that learns their assessments of a feed of tweets, shows its predictions of whether a user would find other tweets (in)accurate, and evolves according to the user feedback. We study how users perceive such an AI, and whether the AI predictions influence users’ judgment. We find that this influence does exist and it grows larger over time, but it is reduced when users provide reasoning for their assessment. We draw from our empirical observations to identify design implications and directions for future work.

A new approach to online discussion, which situates student discussions in the margins of the course content, can enhance student engagement with course materials. However, in high-enrollment classes, the large number of comments can overwhelm and intimidate students. Some become frustrated by the volume of potential online interactions and by a perceived lack of immediate relevance to their studies. Likewise, instructors are disappointed when outstanding discussions, that they deem valuable for all to see, get lost in the clutter. To address these challenges, we propose visual spotlighting mechanisms for increasing the saliency of selected comments. We piloted and deployed multiple designs in two high-enrollment biology courses at a large public university in the United States. Interviews, surveys, and a controlled experiment show that spotlighting relevant comments in heavily annotated texts positively affects students' engagement, measured in terms of their attention to comments, and their reported sense of validation and pride. Students also reported their preferences for certain spotlighting designs.

While digital assistants are increasingly used to help with various productivity tasks, less attention has been paid to employing them in the domain of business documents. To build an agent that can handle users' information needs in this domain, we must first understand the types of assistance that users desire when working on their documents. In this work, we present results from two user studies that characterize the information needs and queries of authors, reviewers, and readers of business documents. In the first study, we used experience sampling to collect users' questions in-situ as they were working with their documents, and in the second, we built a human-in-the-loop document Q&A system which rendered assistance with a variety of users' questions. Our results have implications for the design of document assistants that complement AI with human intelligence including whether particular skillsets or roles within the document are needed from human respondents, as well as the challenges around such systems.

Platform operators have devoted significant effort to combating misinformation on behalf of their users. Users are also stakeholders in this battle, but their efforts to combat misinformation go unsupported by the platforms. In this work, we consider three new user affordances that give social media users greater power in their fight against misinformation: (1) the ability to provide structured accuracy assessments of posts, (2) user-specified indication of trust in other users, and (3) and user configuration of social feed filters according to assessed accuracy. To understand the potential of these designs, we conducted a need-finding survey of 192 people who share and discuss news on social media, finding that many already act to limit or combat misinformation, albeit by repurposing existing platform affordances that lack customized structure for information assessment. We then conducted a field study of a prototype social media platform that implements these user affordances as structured inputs to directly impact how and whether posts are shown. The study involved 14 participants who used the platform for a week to share news while collectively assessing their accuracy. We report on users' perception and use of these affordances. We also provide design implications for platforms and researchers based on our empirical observations.

Headlines play a critical role in how users perceive articles. But many headline publishers craft headlines in ways that either attract clicks in an attempt to earn ad revenue, or misinform users or manipulate their opinions for malicious intents. Such headlines can do harm since many users simply skim and share headlines without reading the articles in full. We present an exploratory browser extension that empowers users to suggest headlines they deem better for news articles. Users can view headlines suggested by other users that they follow as they browse websites. We conducted a study of 27 users who used the extension for one week to read news and suggest headlines. We found that users saw value in the tool and used it to change headlines that they found in need of improvement. We characterize the changes that people make to headlines if enabled. We also report on a followup study we conducted with 312 participants to evaluate headlines suggested by the tool. The purpose of the study was to examine whether headlines suggested by untrained users could be preferred over original headlines by professional editors. We found that a substantial number of the suggested headlines were indeed preferred. Our work explores the designs for, and opportunities and consequences of, empowering news consumers by giving them control over the content curation process.

When users on social media share content without considering its veracity, they may unwittingly be spreading misinformation. In this work, we investigate the design of lightweight interventions that nudge users to assess the accuracy of information as they share it. Such assessment may deter users from posting misinformation in the first place, and their assessments may also provide useful guidance to friends aiming to assess those posts themselves. In support of lightweight assessment, we first develop a taxonomy of the reasons why people believe a news claim is or is not true; this taxonomy yields a checklist that can be used at posting time. We conduct evaluations to demonstrate that the checklist is an accurate and comprehensive encapsulation of people's free-response rationales. In a second experiment, we study the effects of three behavioral nudges---1) checkboxes indicating whether headings are accurate, 2) tagging reasons (from our taxonomy) that a post is accurate via a checklist and 3) providing free-text rationales for why a headline is or is not accurate---on people's intention of sharing the headline on social media. From an experiment with 1668 participants, we find that both providing accuracy assessment and rationale reduce the sharing of false content. They also reduce the sharing of true content, but to a lesser degree that yields an overall decrease in the fraction of shared content that is false. Our findings have implications for designing social media and news sharing platforms that draw from richer signals of content credibility contributed by users. In addition, our validated taxonomy can be used by platforms and researchers as a way to gather rationales in an easier fashion than free-response.

We study how the ratings people receive on online labor platforms are influenced by their performance, gender, their rater's gender, and displayed ratings from other raters. We conducted a deception study in which participants collaborated on a task with a pair of simulated workers, who varied in gender and performance level, and then rated their performance. When the performance of paired workers was similar, low-performing females were rated lower than their male counterparts. Where there was a clear performance difference between paired workers, low-performing females were preferred over a similarly-performing male peer. Furthermore, displaying an average rating from other raters made ratings more extreme, resulting in high performing workers receiving significantly higher ratings and low performers lower ratings compared to when average ratings were absent. This work contributes an empirical understanding of when biases in ratings manifest, and offers recommendations for how online work platforms can counter these biases.

Recommender systems are commonly used in entertainment, news, e-commerce, and social media. Document recommendation is a new and under-explored application area, in which both re-finding and discovery of documents need to be supported. In this paper we provide an initial exploration of users' experience with recommended documents, with a focus on how prior interactions influence recognition and interest. Through a field study of more than 100 users, we investigate the effects of past interactions with recommended documents on users' recognition of, prior intent to open, and interest in the documents. We examined different presentations of interaction history, and the recency and richness of prior interaction. We found that presentation only influenced recognition time. Our findings also indicate that people are more likely to recognize documents they had accessed recently and to do so more quickly. Similarly, documents that people had interacted with more deeply were also more frequently and quickly recognized. However, people were more interested in older documents or those with which they had less involved interactions. This finding suggests that in addition to helping users quickly access documents they intend to re-find, document recommendation can add value in helping users discover other documents. Our results offer implications for designing document recommendation systems that help users fulfil different needs.

Personalized document recommendation systems aim to provide users with a quick shortcut to the documents they may want to access next, usually with an explanation about why the document is recommended. Previous work explored various methods for better recommendations and better explanations in different domains. However, there are few efforts that closely study how users react to the recommended items in a document recommendation scenario. We conducted a large-scale log study of users’ interaction behavior with the explainable recommendation on one of the largest cloud document platforms office.com. Our analysis reveals a number of factors, including display position, file type, authorship, recency of last access, and most importantly, the recommendation explanations, that are associated with whether users will recognize or open the recommended documents. Moreover, we specifically focus on explanations and conduct an online experiment to investigate the influence of different explanations on user behavior. Our analysis indicates that the recommendations help users access their documents significantly faster, but sometimes users miss a recommendation and resort to other more complicated methods to open the documents. Our results suggest opportunities to improve explanations and more generally the design of systems that provide and explain recommendations for documents.

How can instructors group students into teams that interact and learn effectively together? One strand of research advocates for grouping students into teams with "good" compositions such as skill diversity. Another strand argues for deploying team-building activities to foster interpersonal relations like psychological safety. Our work synthesizes these two strands of research. We describe an experiment (N=249) that compares how team composition vs. team-building activities affect student team outcomes. In two university courses, we composed student teams either randomly or using a criteria-based team formation tool. Teams further performed team-building activities that promoted either team or task outcomes. We collected project scores, and used surveys to measure psychological safety, perceived performance, and team satisfaction. Surprisingly, the criteria-based teams did not statistically differ from the random teams on any of the measures taken, despite having compositions that better satisfied the criteria defined by the instructor. Our findings argue that, for instructors deploying a team formation tool, creating an expectation among team members that their team can perform well is as important as tuning the criteria in the tool. We also found that student teams reported high levels of psychological safety, but these levels appeared to develop organically and were not affected by the activities or compositional strategies tested. We distill these and other findings into implications for the design and deployment of team formation tools for learning environments.

Instructors are increasingly using algorithmic tools for team formation, yet little is known about how these tools are applied or how students and instructors perceive their use. We studied a representative team formation tool (CATME) in eight project-based courses. An instructor uses the tool to form teams by surveying students' working styles, skills, and demographics; then configuring these criteria as input into an algorithm that assigns teams. We surveyed students (N=277) in the courses to gauge their perceptions of the strengths and weaknesses of the tool and ideas for improving it. We also interviewed instructors (N=13) different from those who taught the eight courses to learn about their criteria selections and perceptions of the tool. Students valued the rational basis for forming teams but desired a stronger voice in criteria selection and explanations as to why they were assigned to a particular team. Instructors appreciated the efficiency of team formation but wanted to view exemplars of criteria used in similar courses. This work contributes recommendations for deploying team formation tools in educational settings and for better satisfying the goals of all stakeholders.