cs.HC Computer Science
Human-Computer Interaction papers on arXiv
Follow interaction design, user studies, accessibility, and human-centered computing in cs.HC. Search for the user activity or population you study rather than relying only on interface terminology.
1,036 papers indexed
Follow the whole category with the official cs.HC RSS feed, or use a personal filter to select keywords and authors. See the arXiv RSS feed guide for setup and the category guide for primary and cross-listed subjects.
Filter ideas for Human–Computer Interaction
How filters workA method such as interview or usability can be combined with a product context. Do not infer study quality from a keyword match; open the paper to check its participants, methods, and limitations.
- Try filter
Accessibility
Add a context such as mobile, screen reader, or education to focus on relevant interaction settings.
Category cs.HC + abstract contains “accessibility” - Try filter
Human–AI collaboration
Add AI, assistant, or decision making to narrow collaborative-system studies.
Category cs.HC + abstract contains “collaboration”
Examples are starting points. Preview them before saving; keyword matches do not assess a paper’s quality. Recent papers below use the primary category; saved category filters also match cross-listed categories.
LATEST SUBMISSIONS
Recent Human-Computer Interaction papers
Ivy Pham, Akshay Swaminathan, Sebastian Garcia, Jaimie Lim, Gloria Ye, Divyanjali Verma, Alan Pham, Chastin Chung, Shreya Shah, Shaked Azzam, Sharang Phadke, Ivan Lopez, William Wang, Angelina Wang, Nigam H. Shah
Abstract
Background: AI systems are increasingly deployed to support mental health clinicians, yet real-world evidence remains limited. In crisis counseling, where clients often seek human connection, understanding whether AI augmentation preserves or undermines meaningful human engagement is essential. Methods: In a mixed-methods study of a counselor-facing AI copilot on a WhatsApp-based crisis hotline in India (Mar.-Oct. 2025), counselors could request, edit, and send AI messages. We analyzed 20 interviews, 8 shadowing sessions, 56 survey responses, and edits in 27,778 copilot messages from 108 counselors via thematic analysis (Technology Acceptance Model 2, plus inductive coding of emergent factors), and survey statistics. Results: Counselors reported high copilot acceptance (survey): 98.2% found it helpful; 89.3% likely to continue use; 80.4% reported efficiency gains. Interviews highlighted sentence scaffolding, empathetic phrasing, stress reduction, catching missed details, and efficiency. Barriers (survey) included repetitive outputs (23.2%), lack of context (17.9%), and authenticity concerns (10.7%). While 69.6% (survey) reported skill enhancement, interviews surfaced skill atrophy concerns. Counselors frequently accepted copilot suggestions, editing to remove questions, adjust tone, or personalize style. Conclusion: In one of the largest real-world deployments of a counselor-facing mental health AI copilot, counselors reported reduced cognitive load, empathetic communication, and greater efficiency, alongside concerns about skill atrophy, authenticity, and over-reliance. In settings like crisis counseling where clients seek human connection, AI tools must balance operational support with preserving clinical skill and genuine therapeutic engagement. Designs soliciting approval or editing of complete drafts may overweight efficiency at the expense of sustained human engagement.
Suvadeep Maiti, Keya Sinha, Raju S. Bapi
Abstract
Automatic sleep staging models are predominantly developed on healthy sleepers and generalize poorly to clinical populations with fragmented sleep. Across three cohorts (patients with stroke, isolated REM sleep behaviour disorder, and other sleep disorders), we observe 2-3x more awakenings per hour, nearly twice as much N1, and less REM sleep than in healthy sleepers. We propose a label-efficient teacher-student framework for wearable-scale sleep staging. SleepGPT (136M parameters), adapted using labels from 25% of training patients, supervises a causal CNN-GRU (31k parameters; 122 KB) that stages EEG, EOG, or both in real time. We introduce Gcv-TAD, a new black-box transition-aware distillation loss. It emphasizes uncommon stage transitions while discounting those that vary across patients, using a prior estimated from labelled patients. In patient-wise 10-fold cross-validation, Gcv-TAD improves per-patient macro F1 over supervised training on the same labels by +3.2 to +7.6 points on average. Gains are largest on N1, and performance approaches full-label training.
Orit Shaer, Mary Calabro, Zoe Mitchell, Angelora Cooper, Raffaella Sadun, Andrew L. Kun, Osnat Mokryn
Abstract
Remote collaborative platforms increasingly integrate generative AI to support group ideation. These platforms are sociotechnical configurations in which spatial mediation, interaction modality, AI output format, and the mechanisms that make contributions visible to a group co-vary as properties of a deployed system. This paper examines how such configurations shape participants' collaboration and their engagement with AI during creative work. We report a comparative study of two commercially available platforms that instantiate contrasting configurations: a planar shared canvas with text-based AI integration, and an immersive virtual reality workspace with concise AI output embedded in the shared space. Fourteen all-women triads completed a structured ideation task consisting of human-only idea generation, AI-supported idea expansion, and group convergence. We analyzed collaboration patterns, selection of AI-generated ideas, perceived idea quality, workload, presence, and their lexical characteristics. The immersive configuration yielded greater spatial presence and introduced a participation paradox, in which spatial freedom enabled exploration and fragmented group coherence; it was also associated with more balanced role distribution during convergence, at the cost of higher physical demand. In both configurations, AI multiplied the idea pool, and ideas groups authored with AI available were rated above participants' own. AI output format: about 21 words per idea on the planar canvas and 3 in the immersive workspace. Tracked how participants evaluated AI-generated ideas and how often they selected them unaltered as finalists. Neither configuration made AI contributions visible or attributable to the group: participants invoked AI individually and asynchronously in both. We derive design implications for AI output format, group-visible AI invocation, and spatial support for convergence
Niklas Roethlingshoefer, Emma Winkler, Melanie Loeffler, Emely Rosbach
Abstract
As symptom checkers based on artificial intelligence (AI) are becoming common entry points for health information, their influence on lay users' diagnostic decisions raises questions about trust and bias. Of particular concern is confirmation bias, the tendency to favour information that supports one's existing belief while discounting information that contradicts it. One of the central design choices for such systems is the style of voice: whether they should present themselves with a human-like (anthropomorphic) or a clearly machine-like (xenomorphic) voice. This study investigates whether the voice design of an AI symptom checker modulates confirmation bias in self-diagnosis. In a within-subjects online experiment (N = 81 participants, 648 trials), participants selected a diagnosis and rated their confidence, then heard an AI-generated recommendation that either confirmed or contradicted their initial choice, delivered by an anthropomorphic or a machine-like voice, before deciding again. We observed a strong, direction-dependent influence of the AI: participants revised their diagnosis in 45.7% of trials when the AI contradicted them versus 1.2% when it confirmed them (generalised linear mixed model, GLMM, p < .001); confidence rose under confirmation but barely moved under contradiction (robust linear mixed model, p < .001); and decisions took longer after contradiction (Gamma GLMM, p < .001). This effect did not differ between the two voices (no voice or interaction term was significant, smallest p = .282), even though a manipulation check confirmed the voices were perceived as markedly different. The findings suggest that the direction of an AI recommendation, rather than the anthropomorphism of its voice, drives confirmation-related bias in AI-assisted self-diagnosis.
Annika Bush, Melika Minnaar, Salys Sultan, Tasnimul Hasan Tashin, Ankur Bhatt, Meltem Aksoy
Abstract
Multilingual speakers choose languages by topic and conversation partner. Large language models (LLMs) support these languages unequally. Research on code-switching with conversational AI has mostly examined bilingual pairs of well-resourced languages. In Curaçao and Aruba, many people use Dutch, English, Spanish, and the low-resource Creole Papiamentu/o. In a preregistered study, 42 university students held two five-minute chatbot conversations, one about university life and one about local food and culture. Surveys assessed language background, AI use, and switching comfort. 20 international students in Curaçao formed a comparison sample. Participants switched between turns and rarely mixed languages within a message. English dominated both conversations. Participants switched more often in the cultural conversation, where Papiamentu/o and Spanish rose from 15% to 24% of messages. Self-reports showed no lower comfort switching with the chatbot than with a person. Conversational agents must follow turn-by-turn language changes and handle local low-resource languages well.
Frequently asked questions
How do I get alerts for new Human-Computer Interaction papers on arXiv?
Create a filter for the cs.HC category — add keywords or authors to narrow it further if you like. Matching papers are delivered to a personal RSS feed, and optionally by immediate, daily, or weekly email digest.
Where does this Human-Computer Interaction paper data come from?
Paper metadata comes directly from arXiv through its official OAI-PMH feed, checked roughly every 15 minutes for new submissions in cs.HC and every other arXiv category.