As people increasingly turn to AI for personal deliberation beyond task-oriented assistance, concerns about sycophancy in these value-laden contexts have grown. Unlike human flattery, which is intentional and self-interested, AI sycophancy emerges as a byproduct of RLHF’s reward structure for user-preference alignment. Yet the observable behavior is similar: both produce responses that preserve what users want to hear. Focusing on this phenomenon through Goffman’s face-work framework, we operationalize AI sycophancy as excessive face-saving, either active (preserving positive face through agreement) or passive (preserving negative face by withholding challenge). In a mixed-methods study (N=31), participants engaged with AI across three moral dilemmas under these conditions and a non-sycophantic neutral baseline. Sycophantic responses increased decision confidence but reduced open-minded thinking; participants felt supported yet found the conversations unproductive. Neutral responses, though initially uncomfortable, promoted cognitive flexibility and meaningful deliberation. These findings reveal a confidence-competence trade-off in AI-mediated moral reasoning and suggest that effective AI for personal deliberation requires calibrated friction, not unconditional agreement.

Public Warning Systems (PWS) are critical infrastructures for protecting lives during emergencies, yet many users increasingly ignore or disable alerts. Prior research has focused on attentive recipients, overlooking those who disengage mentally or behaviorally. We examine disengagement as a gradual process of psychological detachment shaped by alert fatigue, trust erosion, and perceived inefficacy. Focusing on South Korea’s high-frequency cell broadcast system, averaging 80 messages per day, we conducted a qualitative study with 37 participants classified as responders, ignorers, or blockers, drawing on EPPM and PADM. Through interactive message evaluation and interviews, we traced cognitive and emotional pathways from message reception to protective action or inaction. Our findings reveal structural and psychological barriers, including fixed cognitive anchors that preemptively dismiss alerts, information-seeking behaviors rarely leading to action, and divergent adaptations to repeated false alarms. We reframe emergency alerts as adaptive user–system interfaces shaped by cumulative experience, not static channels. We show how PADM pathways become non-linear, truncated, or collapsed under saturated alert environments. We contribute design implications for more adaptive, trustworthy, and user-sensitive emergency alert systems.

Generative information retrieval (GenIR) enables users to obtain synthesized information through iterative interaction with LLMs, fundamentally reshaping how AI-generated content is produced and consumed. Within this shift, users may encounter AI-generated informational content through two primary pathways: actively creating it themselves or consuming content generated by others. We examine whether authorship biases evaluation---whether users judge AI output from their own interactions more favorably than equivalent output from others. In a mixed-methods experiment (N=28, 2×2 within-subjects), participants interacted with an AI system to retrieve and craft information, then evaluated both their own result and equivalent output generated through the same process but framed as someone else's. Results reveal a selective authorship bias: participants rated self-obtained information significantly higher in quality, but showed no corresponding difference in trust. This pattern suggests that hallucination-aware skepticism constrained trust judgments, but could not prevent quality-driven selection behavior, even in the presence of information conflicts. Given that iterative interactions are inherent to GenIR, diverse interventions seem needed to support users' critical evaluation.

While artificial intelligence (AI) is transforming UX design, its application often remains fragmented, focusing on isolated tasks like visualization rather than the cohesive research process. To address this gap, we present UREKA, a novel research assistant prototype designed to support the entire UX research workflow, from ideation and data analysis to planning and insight generation. We conducted a mixed-methods evaluation with 16 UX designers. The prototype achieved a System Usability Scale (SUS) score of 80.5, indicating excellent usability. Qualitative findings show participants praised UREKA’s ability to streamline research tasks and generate nuanced, project-specific personas. However, they also identified challenges, including the risk of generalized AI responses and an initial learning curve. Our findings demonstrate that an integrated AI tool like UREKA can significantly enhance research efficiency and support informed design decisions, highlighting a collaborative model where AI serves as a “cognitive accelerator” while the designer retains critical oversight.

Empirical research on perception and cognition has laid the foundation for visualization design, often distilled into practical guidelines intended to support effective chart creation. However, it remains unclear how well these research-driven insights are reflected in the guidelines practitioners actually use. In this paper, we investigate the research-practice gap in visualization design guidelines through a mixed-methods approach. We first collected design guidelines from practitioner-facing sources and empirical studies from academic venues to assess their alignment. To complement this analysis, we conducted surveys and interviews with practitioners and researchers to examine their experiences, perceptions, and challenges surrounding the development and use of design guidelines. Our findings reveal misalignment between empirical evidence and widely used guidelines, differing perspectives between communities, and key barriers that contribute to the persistence of the research-practice gap.

Conversational argument search systems influence how users access diverse perspectives but are prone to selective exposure. To address this, we propose two strategies: an interface-level multi-agent framework that structures perspective presentation and an interaction-level questioning strategy that encourages deeper engagement. We evaluate these strategies through a 2 x 2 factorial user study, examining their impact on selective exposure. Results show that the multi-agent setup facilitates broader perspective comparison, while agent-initiated questioning fosters deeper reflection; together, they promote more balanced argument access. Based on these findings, we discuss conversational search systems to mitigate selective exposure by implementing multi-agent interactions and questioning mechanisms.

With the advancement of AI, even people without professional experience can create artworks using AI-based image generation systems like DALL-E 2. However, little is known about how users interact with these new AI algorithms, much less how AI-infused systems can be designed. We explore the user experience of these new technologies and their potential to foster creativity. A user study was carried out where 13 participants executed tasks of creating artworks using DALL-E 2 alongside in-depth interviews related to their experience. The results showed that users had ambivalent opinions regarding the algorithm’s performance. When users were informed of the system’s capabilities, they subsequently utilized more specific prompts to generate the intended output. Users also optimized their prompts (the queries they entered to create artworks) based on how algorithms worked to achieve their desired outcome. The users wanted a two-way interaction where AI explained the outcome and accepted feedback rather than simply accepting unilateral instructions. We discuss the implications for designing interfaces that maximize creativity while providing comfort for the users.

This study investigates effective feedback mechanisms to maintain human engagement in interactive machine learning (IML) systems, focusing on social media platforms. We developed “Loop,” an IML system based on human-in-the-loop (HITL) principles that recommends content while encouraging users to report inaccuracies for model refinement. Loop implements three types of artificial intelligence (AI) feedback on user reports: (a) machine learning (ML)-centric, (b) personal-centric, and (c) community-centric feedback. In addition, we evaluated the relative effectiveness of these feedback types under two different task criticality scenarios: high and low. A user study with 30 participants was conducted to evaluate Loop through questionnaires and interviews. Results showed that participants preferred algorithmic improvements for personal benefit over altruistic contributions to the community, especially for low-criticality tasks. Furthermore, personal-centric feedback had a significant impact on user engagement and satisfaction. Our findings provide insights into the effectiveness of machine feedback in HITL-ML systems, contributing to the design of more engaging and effective IML interfaces. We discuss implications and strategies for encouraging proactive user engagement in HITL-ML-based systems, emphasizing the importance of tailored feedback mechanisms.

Users are increasingly exposed to AI-generated language, presenting potential deception and communication risks. This study delved into the rhetorical aspect of AI-generated language influencing users’ truth discernment. We conducted a user study comparing three levels of rhetorical presence and four persuasive rhetorical elements, using interviews to understand users’ truth-detection methods. Results showed that outputs with fewer rhetorical elements posed challenges for users in distinguishing truth from false, while those with more rhetoric often misled users into false truths. Users’ AI expectations influenced truth judgments, with responses meeting expectations perceived as more truthful. Casual, human-like responses were often deemed false, while technical, precise AI responses were preferred. This research emphasizes that rhetorical elements of AI language can significantly bias individuals regardless of a statement’s actual truth. For enhanced transparency in human-AI communication, it is advisable for AI designs to thoughtfully integrate rhetorical elements and establish guiding principles aimed at minimizing the potential for deceptive responses.

Music is intrinsically connected to human experience, yet the plethora of choices often renders the search for the ideal piece perplexing, especially when the search terms are ambiguous. This study questions the viability of employing visual data, specifically images, in innovative queries for music search, and it aims to better align search results with users’ moods and situational context. We designed and evaluated three prototype systems for music search—TTTune (text-based), VisTune (image-based), and VTTune (hybrid)—to comparatively assess user experience and system usability. In a comprehensive user study involving 236 participants, each participant interacted with one of the systems and subsequently completed post-experimental surveys. A subset of participants also participated in in-depth interviews to further elucidate the potential and the advantages of image-based music retrieval (IMR) systems. Our findings reveal a marked preference for the user experience and usability offered by the IMR approach, as compared with the traditional text-based method. This underscores the potential of the image in an effective search query. Based on these findings, we discuss interface design guidelines tailored for IMR systems and factors affecting system performance, contributing to the evolving landscape of music search methods.

Large language models (LLMs) have facilitated significant strides in generating conversational agents, enabling seamless, contextually relevant dialogues across diverse topics. However, the existing LLM-driven conversational agents have fixed personalities and functionalities, limiting their adaptability to individual user needs. Creating personalized agent personas with distinct expertise or traits can address this issue. Nonetheless, we lack knowledge of how people customize and interact with agent personas. In this research, we investigated how users customize agent personas and their impact on interaction quality, diversity, and dynamics. To this end, we developed CloChat, an interface supporting easy and accurate customization of agent personas in LLMs. We conducted a study comparing how participants interact with CloChat and ChatGPT. The results indicate that participants formed emotional bonds with the customized agents, engaged in more dynamic dialogues, and showed interest in sustaining interactions. These findings contribute to design implications for future systems with conversational agents using LLMs.

In our increasingly diverse society, everyday physical interfaces often present barriers, impacting individuals across various contexts. This oversight, from small cabinet knobs to identical wall switches that can pose different contextual challenges, highlights an imperative need for solutions. Leveraging low-cost 3D-printed augmentations such as knob magnifiers and tactile labels seems promising, yet the process of discovering unrecognized barriers remains challenging because disability is context-dependent. We introduce AccessLens, an end-to-end system designed to identify inaccessible interfaces in daily objects, and recommend 3D-printable augmentations for accessibility enhancement. Our approach involves training a detector using the novel AccessDB dataset designed to automatically recognize 21 distinct Inaccessibility Classes (e.g., bar-small and round-rotate) within 6 common object categories (e.g., handle and knob). AccessMeta serves as a robust way to build a comprehensive dictionary linking these accessibility classes to open-source 3D augmentation designs. Experiments demonstrate our detector’s performance in detecting inaccessible objects.

Delivery robots are increasingly becoming part of our urban landscape. However, the general public is divided about their presence in public spaces; some welcome their usefulness, while others see them as intrusive or even threatening. This study aims to understand users' perceptions of these robots to provide concrete insights into their further development. First, we used text mining to analyze people's reactions to popular YouTube videos featuring delivery robots. Based on these findings, we applied the scenario-based design method to develop scenarios illustrating user interactions with delivery robots. We then conducted in-depth interviews with 30 participants to explore their views on these scenarios. Our analysis highlighted several design issues, including robots' aesthetics, interactions with pedestrians, and the broader physical and regulatory framework. We also identified common concerns and positive expectations for these robots. From these findings, we propose design implications for the future of delivery robots.

Advances in artificial intelligence have enabled unprecedented technical capabilities, yet making these advances useful in the real world remains challenging. We engaged in a Research through Design process to improve the ideation of AI products and services. We developed a design resource capturing AI capabilities based on 40 AI features commonly used across various domains. To probe its usefulness, we created a set of slides illustrating AI capabilities and asked designers to ideate AI-enabled user experiences. We also incorporated capabilities into our own design process to brainstorm concepts with domain experts and data scientists. Our research revealed that designers should focus on innovations where moderate AI performance creates value. We reflect on our process and discuss research implications for creating and assessing resources to systematically explore AI’s problem-solution space.

When creating a visualization, designers face various conflicting design choices. They typically rely on their hunches to deal with intricate trade-offs or resort to feedback from their colleagues. On the other hand, researchers have long used empirical methods to derive useful quantitative insights into visualization designs. Taking inspiration from this research tradition, we developed VisLab, an open-source online system to complement the existing qualitative feedback practice and help visualization practitioners run experiments to gather empirically informed design feedback. We surveyed practitioners’ perceptions of quantitative feedback and analyzed the research literature to inform VisLab’s motivation and design. VisLab operationalizes the experiment process using templates and dashboards to make empirical methods amenable for practitioners while supporting sharing and remixing experiments to aid knowledge exchange and validation. We demonstrated the validity of experiments in VisLab and evaluated the usability and potential usefulness of VisLab in visualization design practice.

HCI research has explored AI as a design material, suggesting that designers can envision AI’s design opportunities to improve UX. Recent research claimed that enterprise applications offer an opportunity for AI innovation at the user experience level. We conducted design workshops to explore the practices of experienced designers who work on cross-functional AI teams in the enterprise. We discussed how designers successfully work with and struggle with AI. Our findings revealed that designers can innovate at the system and service levels. We also discovered that making a case for an AI feature’s return on investment is a barrier for designers when they propose AI concepts and ideas. Our discussions produced novel insights on designers’ role on AI teams, and the boundary objects they used for collaborating with data scientists. We discuss the implications of these findings as opportunities for future research aiming to empower designers in working with data and AI.

Individuals interact with algorithms in various ways. Users even game and circumvent algorithms so as to achieve favorable outcomes. This study aims to come to an understanding of how various stakeholders interact with each other in tricking algorithms, with a focus towards online review communities. We employed a mixed-method approach in order to explore how and why users write machine non-translatable reviews as well as how those encrypted messages are perceived by those receiving them. We found that users are able to find tactics to trick the algorithms in order to avoid censoring, to mitigate interpersonal burden, to protect privacy, and to provide authentic information for enabling the formation of informative review communities. They apply several linguistic and social strategies in this regard. Furthermore, users perceive encrypted messages as both more trustworthy and authentic. Based on these findings, we discuss implications for online review community and content moderation algorithms.

Artificial intelligence (AI) algorithms are making remarkable achievements even in creative fields such as aesthetics. However, whether those outside the machine learning (ML) community can sufficiently interpret or agree with their results, especially in such highly subjective domains, is being questioned. In this paper, we try to understand how different user communities reason about AI algorithm results in subjective domains. We designed AI Mirror, a research probe that tells users the algorithmically predicted aesthetic scores of photographs. We conducted a user study of the system with 18 participants from three different groups: AI/ML experts, domain experts (photographers), and general public members. They performed tasks consisting of taking photos and reasoning about AI Mirror's prediction algorithm with think-aloud sessions, surveys, and interviews. The results showed the following: (1) Users understood the AI using their own group-specific expertise; (2) Users employed various strategies to close the gap between their judgments and AI predictions overtime; (3) The difference between users' thoughts and AI pre-dictions was negatively related with users' perceptions of the AI's interpretability and reasonability. We also discuss design considerations for AI-infused systems in subjective domains.

Although group chat discussions are prevalent in daily life, they have a number of limitations. When discussing in a group chat, reaching a consensus often takes time, members contribute unevenly to the discussion, and messages are unorganized. Hence, we aimed to explore the feasibility of a facilitator chatbot agent to improve group chat discussions. We conducted a needfinding survey to identify key features for a facilitator chatbot. We then implemented GroupfeedBot, a chatbot agent that could facilitate group discussions by managing the discussion time, encouraging members to participate evenly, and organizing members' opinions. To evaluate GroupfeedBot, we performed preliminary user studies that varied for diverse tasks and different group sizes. We found that the group with GroupfeedBot appeared to exhibit more diversity in opinions even though there were no differences in output quality and message quantity. On the other hand, GroupfeedBot promoted members' even participation and effective communication for the medium-sized group.

Automated journalism refers to the generation of news articles using computer programs. Although it is widely used in practice, its user experience and interface design remain largely unexplored. To understand the user perception of an automated news system, we designed NewsRobot, a research prototype that automatically generated news on major events of the PyeongChang 2018 Winter Olympic Games in real-time. It produces six types of news by combining two kinds of content (general/individualized) and three styles (text, text+image, text+image+sound). A total of 30 users participated in using NewsRobot, completing surveys and interviews on their experience. Our findings are as follows: (1) Users preferred individualized news yet considered it less credible, (2) more presentation elements were appreciated but only if their quality was assured, and (3) NewsRobot was considered factual and accurate yet shallow in depth. Based on our findings, we discuss implications for designing automated journalism user interfaces.

Recent advances in artificial intelligence (AI) have increased the opportunities for users to interact with the technology. Now, users can even collaborate with AI in creative activities such as art. To understand the user experience in this new user--AI collaboration, we designed a prototype, DuetDraw, an AI interface that allows users and the AI agent to draw pictures collaboratively. We conducted a user study employing both quantitative and qualitative methods. Thirty participants performed a series of drawing tasks with the think-aloud method, followed by post-hoc surveys and interviews. Our findings are as follows: (1) Users were significantly more content with DuetDraw when the tool gave detailed instructions. (2) While users always wanted to lead the task, they also wanted the AI to explain its intentions but only when the users wanted it to do so. (3) Although users rated the AI relatively low in predictability, controllability, and comprehensibility, they enjoyed their interactions with it during the task. Based on these findings, we discuss implications for user interfaces where users can collaborate with AI in creative works.

In this paper, we present Touch+Finger, a new interaction technique that augments touch input with multi-finger gestures for rich and expressive interaction. The main idea is that while one finger is engaged in a touch event, a user can leverage the remaining fingers, the "idle" fingers, to perform a variety of hand poses or in-air gestures to extend touch-based user interface capabilities. To fully understand the use of these idle fingers, we constructed a design space based on conventional touch gestures (i.e., single- and multi-touch gestures) and inter- action period (i.e., before and during touch). Considering the design space, we investigated the possible movement of the idle fingers and developed a total of 20 Touch+Finger gestures. Using ring-like devices to track the motion of the idle fingers in the air, we evaluated the Touch+Finger gestures on both recognition accuracy and ease of use. They were classified with a recognition accuracy of over 99% and received positive and negative comments from 8 participants. We suggested 8 interaction techniques with Touch+Finger gestures that demonstrate extended touch-based user interface capabilities.

Various forms of artificial intelligence (AI), such as Apple's Siri and Google Now, have permeated our everyday lives. However, the advent of such "human-like" technology has stirred both awe and a great deal of fear. Many consider it a woe to have an unimaginable future where human intelligence is exceeded by AI. This paper investigates how people perceive and understand AI with a case study of the Google DeepMind Challenge Match, a Go match between Lee Sedol and AlphaGo, in March 2016. This study explores the underlying and changing perspectives toward AI as users experienced this historic event. Interviews with 22 participants show that users tacitly refer to AlphaGo as an "other" as if it were comparable to a human, while dreading that it would come back to them as a potential existential threat. Our work illustrates a confrontational relationship between users and AI, and suggests the need to prepare for a new kind of user experience in this nascent socio- technological change. It calls for a collaborative research effort from the HCI community to study and accommodate users for a future where they interact with algorithms, not just interfaces.

The use of car navigation system is very common nowadays. Most of the car navigation services are based on turn-by-turn instructions and distance calculations. Academic research in this field has focused on evaluating basic usability. However, such products and studies have not covered users' various needs that arise in specific driving situations. For example, in a complex city space, drivers often face burdensome problems, especially when picking up pedestrians. We conducted a semistructured online survey asking specific problems, work-arounds, and their suggestions in picking-up situations. We grouped responses into several issue points based on their similarities and induced design implications for a car navigation system supporting picking-up situations. Through this user-centered design approach, we developed "Gravity - Automatic Location Tracking System between a Car and a Pedestrian" as a prototype and evaluated its usability, and we received favorable feedback.