arXiv subjects

Koji Yatani

Publications and source records attributed to Koji Yatani.

At least 19 recordsLinked to original sources

arXiv2026

Two Modes of Reflection: How Temporal, Spatial, and Social Distances Affect Reflective Writing in Family Caregiving

Therapeutic writing offers significant benefits for well-being; however, for family caregivers, conventional fixed or user-initiated schedules often fail to align with their dynamic, high-stress reality. We conducted a three-week field study with 47 caregivers using a chatbot that delivered daily reflective writing cues and captured temporal, spatial, and social contexts. Our analysis identified a writing spectrum anchored by two distinct reflective modes. Under psychologically proximal conditions, participants produced detailed, emotion-rich, and care-recipient-focused narratives that supported emotional release. Under distal conditions, they generated calmer, self-focused, and analytic accounts that enabled objective reflection and cognitive reappraisal. Participants described trade-offs: proximity preserved vivid detail but limited objectivity, while distance enabled analysis but risked memory loss. This work contributes empirical evidence of how psychological distances shape reflective writing and proposes design implications for distance-aware Just-in-Time Adaptive Interventions for family caregivers' mental health support.

cs.HC↗

arXiv2026

From Voice to Value: Leveraging AI to Enhance Spoken Online Reviews on the Go

Online reviews help people make better decisions. Review platforms usually depend on typed input, where leaving a good review requires significant effort because users must carefully organize and articulate their thoughts. This may discourage users from leaving comprehensive and high-quality reviews, especially when they are on the go. To address this challenge, we developed Vocalizer, a mobile application that enables users to provide reviews through voice input, with enhancements from a large language model (LLM). In a longitudinal study, we analysed user interactions with the app, focusing on AI-driven features that help refine and improve reviews. Our findings show that users frequently utilized the AI agent to add more detailed information to their reviews. We also show how interactive AI features can improve users self-efficacy and willingness to share reviews online. Finally, we discuss the opportunities and challenges of integrating AI assistance into review-writing systems.

cs.HC↗

arXiv2026

Zeitgeist-Aware Multimodal (ZAM) Datasets of Pro-Eating Disorder Short-Form Videos: An Idea Worth Researching

Objective: Reliable identification of pro-eating disorder (pro-ED) content online suffers from two pervasive problems: 1) existing methods predominantly rely on text-based signals, failing to capture the inherently multimodal nature of multimedia content; and 2) these methods struggle to keep pace with the rapid evolution of references, memes, terminology, and contextual cues that underlie this content. Together, these limitations point to a gap: the absence of an expert-annotated reference standard capable of supporting real-time research and robust multimodal detection model training for pro-ED content on short-form video platforms. Method: To address this, we propose "zeitgeist-aware" multimodal (ZAM) datasets: continuously curated collections of annotated multimodal pro-ED content with inclusion criteria that evolve alongside the memetic zeitgeist: the variable essence of what is considered pro-ED as new media and references come into the cultural zeitgeist and are absorbed and interpreted in online spaces. Results: We present a rationale for such datasets, define their core characteristics, outline approaches for their curation, and describe our progress toward that end. Discussion: This dataset and pipeline architecture may benefit researchers across several fields who are interested in how pro-ED sentiment is encoded and transmitted through short-form video content across time, including for the purpose of responsive moderation efforts.

cs.HC↗

arXiv2026

What We Talk About When We Talk About Frameworks in HCI

In HCI, frameworks function as a type of theoretical contribution, often supporting ideation, design, and evaluation. Yet, little is known about how they are actually used, what functions they serve, and which scholarly practices that shape them. To address this gap, we conducted a systematic review of 615 papers from a decade of CHI proceedings (2015-2024) that prominently featured the term framework. We classified these papers into six engagement types. We then examined the role, form, and essential components of newly proposed frameworks through a functional typology, analyzing how they are constructed, validated, and articulated for reuse. Our results show that enthusiasm for proposing new frameworks exceeds the willingness to iterate on existing ones. They also highlight the ambiguity in the function of frameworks and the scarcity of systematic validation. Based on these insights, we call for more rigorous, reflective, and cumulative practices in the development and use of frameworks in HCI.

cs.HC↗

arXiv2026

Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents

Autonomous agents excel in self-improvement through reflection and iterative refinement, which reuse successful task trajectories as in-context examples to assist subsequent reasoning. However, shifting across tasks often introduces a context mismatch. Hence, existing approaches either discard the trajectories or manipulate them using heuristics, leading to a non-negligible fine-tuning cost or unguaranteed performance. To bridge this gap, we reveal a context-trajectory correlation, where shifts of context are highly parallel with shifts of trajectory. Based on this finding, we propose BrIdge contextual gap FoR imprOvised trajectory STeering (Bifrost), a training-free method that leverages context differences to precisely guide the adaptation of previously solved trajectories towards the target task, mitigating the misalignment caused by context shifts. Our trajectory adaptation is conducted at the representation level using agent hidden states, ensuring trajectory transformation accurately aligns with the target context in a shared space. Across diverse benchmarks, Bifrost consistently outperforms existing trajectory reuse and finetuned self-improvement methods, demonstrating that agents can effectively leverage past experiences despite substantial context shifts.

cs.LG↗

arXiv2026

LLM-based In-situ Thought Exchanges for Critical Paper Reading

Critical reading is a primary way through which researchers develop their critical thinking skills. While exchanging thoughts and opinions with peers can strengthen critical reading, junior researchers often lack access to peers who can offer diverse perspectives. To address this gap, we designed an in-situ thought exchange interface informed by peer feedback from a formative study (N=8) to support junior researchers' critical paper reading. We evaluated the effects of thought exchanges under three conditions (no-agent, single-agent, and multi-agent) with 46 junior researchers over two weeks. Our results showed that incorporating agent-mediated thought exchanges during paper reading significantly improved participants' critical thinking scores compared to the no-agent condition. In the single-agent condition, participants more frequently made reflective annotations on the paper content. In the multi-agent condition, participants engaged more actively with agents' responses. Our qualitative analysis further revealed that participants compared and analyzed multiple perspectives in the multi-agent condition. This work contributes to understanding in-situ AI-based support for critical paper reading through thought exchanges and offers design implications for future research.

cs.HC↗

arXiv2026

Conversational Inoculation to Enhance Resistance to Misinformation

Proliferation of misinformation is a globally acknowledged problem. Cognitive Inoculation helps build resistance to different forms of persuasion, such as misinformation. We investigate Conversational Inoculation, a method to help people build resistance to misinformation through dynamic conversations with a chatbot. We built a Web-based system to implement the method, and conducted a within-subject user experiment to compare it with two traditional inoculation methods. Our results validate Conversational Inoculation as a viable novel method, and show how it was able to enhance participants' resistance to misinformation. A qualitative analysis of the conversations between participants and the chatbot reveal independence and trust as factors that boosted the efficiency of Conversational Inoculation, and friction of interaction as a factor hindering it. We discuss the opportunities and challenges of using Conversational Inoculation to combat misinformation. Our work contributes a timely investigation and a promising research direction in scalable ways to combat misinformation.

cs.HC↗

arXiv2026

Understanding Reader Perception Shifts upon Disclosure of AI Authorship

As AI writing support becomes ubiquitous, how disclosing its use affects reader perception remains a critical, underexplored question. We conducted a study with 261 participants to examine how revealing varying levels of AI involvement shifts author impressions across six distinct communicative acts. Our analysis of 990 responses shows that disclosure generally erodes perceptions of trustworthiness, caring, competence, and likability, with the sharpest declines in social and interpersonal writing. A thematic analysis of participants' feedback links these negative shifts to a perceived loss of human sincerity, diminished author effort, and the contextual inappropriateness of AI. Conversely, we find that higher AI literacy mitigates these negative perceptions, leading to greater tolerance or even appreciation for AI use. Our results highlight the nuanced social dynamics of AI-mediated authorship and inform design implications for creating transparent, context-sensitive writing systems that better preserve trust and authenticity.

cs.HC↗

arXiv2025

Examining Input Modalities and Visual Feedback Designs in Mobile Expressive Writing

Expressive writing is an established approach for stress management. Recently, information technologies, such as smartphones, have also been explored for expressive writing. Although mobile interfaces have the potential to support various daily writing activities, interface designs for mobile expressive writing and their effects on stress relief still lack empirical understanding. We examined the interface design of mobile expressive writing by investigating the influence of input modalities and visual feedback designs on usability and perceived cathartic effects through field studies. While our studies confirmed the stress-relieving effects of mobile expressive writing, our results offer important insights into interface design. We found keyboard-based text entry more suited and preferred over voice messages for its privacy and reflective nature. Participants expressed different reasons for preferring different post-writing visual feedback depending on the cause and type of stress. This work advances interface design for mobile expressive writing and deepens understanding of its effects.

cs.HC↗

arXiv2025

OriStitch: A Machine Embroidery Workflow to Turn Existing Fabrics into Self-Folding 3D Textiles

OriStitch is a computational fabrication workflow to turn existing flat fabrics into self-folding 3D structures. Users turn fabrics into self-folding sheets by machine embroidering functional threads in specific patterns on fabrics, and then apply heat to deform the structure into a target 3D structure. OriStitch is compatible with a range of existing materials (e.g., leather, woven fabric, and denim). We present the design of specific embroidered hinges that fully close under exposure to heat. We discuss the stitch pattern design, thread and fabric selection, and heating conditions. To allow users to create 3D textiles using our hinges, we create a tool to convert 3D meshes to 2D stitch patterns automatically, as well as an end-to-end fabrication and actuation workflow. To validate this workflow, we designed and fabricated a cap (303 hinges), a handbag (338 hinges), and a cover for an organically shaped vase (140 hinges). In technical evaluation, we found that our tool successfully converted 23/28 models (textures and volumetric objects) found in related papers. We also demonstrate the folding performance across different materials (suede leather, cork, Neoprene, and felt).

cs.HC↗

arXiv2025

Research as Resistance: Recognizing and Reconsidering HCI's Role in Technology Hype Cycles

The history of information technology development has been characterized by consecutive waves of boom and bust, as new technologies come to market, fuel surges of investment, and then stabilize towards maturity. However, in recent decades, the acceleration of such technology hype cycles has resulted in the prioritization of massive capital generation at the expense of longterm sustainability, resulting in a cascade of negative social, political, and environmental consequences. Despite the negative impacts of this pattern, academic research, and in particular HCI research, is not immune from such hype cycles, often contributing substantial amounts of literature to the discourse surrounding a wave of hype. In this paper, we discuss the relationship between technology and capital, offer a critique of the technology hype cycle using generative AI as an example, and finally suggest an approach and a set of strategies for how we can counteract such cycles through research as resistance.

cs.HC↗

arXiv2024

When Group Spirit Meets Personal Journeys: Exploring Motivational Dynamics and Design Opportunities in Group Therapy

Psychotherapy, such as cognitive-behavioral therapy (CBT), is effective in treating various mental disorders. Technology-facilitated mental health therapy improves client engagement through methods like digitization or gamification. However, these innovations largely cater to individual therapy, ignoring the potential of group therapy-a treatment for multiple clients concurrently, which enables individual clients to receive various perspectives in the treatment process and also addresses the scarcity of healthcare practitioners to reduce costs. Notwithstanding its cost-effectiveness and unique social dynamics that foster peer learning and community support, group therapy, such as group CBT, faces the issue of attrition. While existing medical work has developed guidelines for therapists, such as establishing leadership and empathy to facilitate group therapy, understanding about the interactions between each stakeholder is still missing. To bridge this gap, this study examined a group CBT program called the Serigaya Methamphetamine Relapse Prevention Program (SMARPP) as a case study to understand stakeholder coordination and communication, along with factors promoting and hindering continuous engagement in group therapy. In-depth interviews with eight facilitators and six former clients from SMARPP revealed the motivators and demotivators for facilitator-facilitator, client-client, and facilitator-client communications. Our investigation uncovers the presence of discernible conflicts between clients' intrapersonal motivation as well as interpersonal motivation in the context of group therapy through the lens of self-determination theory. We discuss insights and research opportunities for the HCI community to mediate such tension and enhance stakeholder communication in future technology-assisted group therapy settings.

cs.HC↗

arXiv2024

AI as Extraherics: Fostering Higher-order Thinking Skills in Human-AI Interaction

As artificial intelligence (AI) technologies, including generative AI, continue to evolve, concerns have arisen about over-reliance on AI, which may lead to human deskilling and diminished cognitive engagement. Over-reliance on AI can also lead users to accept information given by AI without performing critical examinations, causing negative consequences, such as misleading users with hallucinated contents. This paper introduces extraheric AI, a human-AI interaction conceptual framework that fosters users' higher-order thinking skills, such as creativity, critical thinking, and problem-solving, during task completion. Unlike existing human-AI interaction designs, which replace or augment human cognition, extraheric AI fosters cognitive engagement by posing questions or providing alternative perspectives to users, rather than direct answers. We discuss interaction strategies, evaluation methods aligned with cognitive load theory and Bloom's taxonomy, and future research directions to ensure that human cognitive skills remain a crucial element in AI-integrated environments, promoting a balanced partnership between humans and AI.

cs.HC↗

arXiv2024

RoCap: A Robotic Data Collection Pipeline for the Pose Estimation of Appearance-Changing Objects

Object pose estimation plays a vital role in mixed-reality interactions when users manipulate tangible objects as controllers. Traditional vision-based object pose estimation methods leverage 3D reconstruction to synthesize training data. However, these methods are designed for static objects with diffuse colors and do not work well for objects that change their appearance during manipulation, such as deformable objects like plush toys, transparent objects like chemical flasks, reflective objects like metal pitchers, and articulated objects like scissors. To address this limitation, we propose Rocap, a robotic pipeline that emulates human manipulation of target objects while generating data labeled with ground truth pose information. The user first gives the target object to a robotic arm, and the system captures many pictures of the object in various 6D configurations. The system trains a model by using captured images and their ground truth pose information automatically calculated from the joint angles of the robotic arm. We showcase pose estimation for appearance-changing objects by training simple deep-learning models using the collected data and comparing the results with a model trained with synthetic data based on 3D reconstruction via quantitative and qualitative evaluation. The findings underscore the promising capabilities of Rocap.

cs.RO↗

arXiv2023

$synapse$: interactive support on photoemission spectroscopy measurement and analysis for non-expert users

Photoemission spectroscopy, an experimental method based on the photoelectric effect, is now an indispensable technique used in various fields such as materials science, life science, medicine, and nanotechnology. However, part of the experimental process of photoemission spectroscopy relies on experience and intuition, which is difficult to understand for novice users. In particular, photoemission spectroscopy experiments using high-brilliance synchrotron radiation as a light source are not easy for novice users because the measurements must be performed quickly and accurately as scheduled within a limited experimental period. In addition, research on the application of information science methods to quantum data measurement, such as photoemission spectroscopy, is mainly aimed at the development of analysis methods, and few attempts have been made to clarify the problems faced by users who lack experience. In this study, we identified the problems faced by novice users of photoemission spectroscopy, implemented a native application with functions to solve these problems, and evaluated it qualitatively and quantitatively. This paper describes the contents of the field study and interview survey, the functional design and implementation of the application based on our field study and interview survey, and the results and discussion of the evaluation experiment.

cond-mat.mtrl-sci↗

arXiv2022

SyncUp: Vision-based Practice Support for Synchronized Dancing

The beauty of synchronized dancing lies in the synchronization of body movements among multiple dancers. While dancers utilize camera recordings for their practice, standard video interfaces do not efficiently support their activities of identifying segments where they are not well synchronized. This thus fails to close a tight loop of an iterative practice process (i.e., capturing a practice, reviewing the video, and practicing again). We present SyncUp, a system that provides multiple interactive visualizations to support the practice of synchronized dancing and liberate users from manual inspection of recorded practice videos. By analyzing videos uploaded by users, SyncUp quantifies two aspects of synchronization in dancing: pose similarity among multiple dancers and temporal alignment of their movements. The system then highlights which body parts and which portions of the dance routine require further practice to achieve better synchronization. The results of our system evaluations show that our pose similarity estimation and temporal alignment predictions were correlated well with human ratings. Participants in our qualitative user evaluation expressed the benefits and its potential use of SyncUp, confirming that it would enable quick iterative practice.

cs.HC↗

arXiv2022

Gesture-aware Interactive Machine Teaching with In-situ Object Annotations

Interactive Machine Teaching (IMT) systems allow non-experts to easily create Machine Learning (ML) models. However, existing vision-based IMT systems either ignore annotations on the objects of interest or require users to annotate in a post-hoc manner. Without the annotations on objects, the model may misinterpret the objects using unrelated features. Post-hoc annotations cause additional workload, which diminishes the usability of the overall model building process. In this paper, we develop LookHere, which integrates in-situ object annotations into vision-based IMT. LookHere exploits users' deictic gestures to segment the objects of interest in real time. This segmentation information can be additionally used for training. To achieve the reliable performance of this object segmentation, we utilize our custom dataset called HuTics, including 2040 front-facing images of deictic gestures toward various objects by 170 people. The quantitative results of our user study showed that participants were 16.3 times faster in creating a model with our system compared to a standard IMT system with a post-hoc annotation process while demonstrating comparable accuracies. Additionally, models created by our system showed a significant accuracy improvement ($ΔmIoU=0.466$) in segmenting the objects of interest compared to those without annotations.

cs.HC↗

arXiv2021

Enhancing Model Assessment in Vision-based Interactive Machine Teaching through Real-time Saliency Map Visualization

Interactive Machine Teaching systems allow users to create customized machine learning models through an iterative process of user-guided training and model assessment. They primarily offer confidence scores of each label or class as feedback for assessment by users. However, we observe that such feedback does not necessarily suffice for users to confirm the behavior of the model. In particular, confidence scores do not always offer the full understanding of what features in the data are used for learning, potentially leading to the creation of an incorrectly-trained model. In this demonstration paper, we present a vision-based interactive machine teaching interface with real-time saliency map visualization in the assessment phase. This visualization can offer feedback on which regions of each image frame the current model utilizes for classification, thus better guiding users to correct the corresponding concepts in the iterative teaching.

cs.HC↗