International Journal of Human-Computer Studies最新文献

{"title":"Detection of social connectedness in everyday life via multimodal lifelogging data","authors":"Chelsea Dobbins ,&nbsp;Stephen Fairclough ,&nbsp;Catherine Haslam ,&nbsp;S. Alexander Haslam ,&nbsp;Sarah Bentley","doi":"10.1016/j.ijhcs.2026.103749","DOIUrl":"10.1016/j.ijhcs.2026.103749","url":null,"abstract":"<div><div>Loneliness, low mood, and social disconnection can have damaging effects on physical and mental health. Detecting these emotions in the context of everyday life is important as these psychological states can manifest differently outside the laboratory. Lifelogging and quantified self technologies, including wearable devices, offer an approach to continuously monitor physiological signals in the real-world. However, little work has been undertaken with these devices to detect social connection in everyday life. This paper presents a study that leveraged machine learning to infer mood and social connectedness in everyday life using multimodal lifelogging data collected via a wrist-worn wearable device. Fifty participants were supplied with a wearable device and smartphone that collected physiological and subjective data across two consecutive weekdays as they went about their daily lives. The analysis examined physiological correlates between a person’s psychological perceptions of general connectedness, as well as feelings of in-the-moment social connection to people within an estimated 5 m vicinity and mood at specific timepoints using four machine learning classification models – k-Nearest Neighbour, Random Forest, Support Vector Machine and Naïve Bayes. Results demonstrated that Random Forest obtained the highest accuracy of 0.8 – 0.84 for the binary detection of mood and social connection in everyday life.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103749"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When trust collides: Exploring human-LLM cooperation intention through the prisoner’s dilemma","authors":"Guanxuan Jiang ,&nbsp;Shirao Yang ,&nbsp;Yuyang Wang ,&nbsp;Pan Hui","doi":"10.1016/j.ijhcs.2026.103740","DOIUrl":"10.1016/j.ijhcs.2026.103740","url":null,"abstract":"<div><div>Large language models (LLMs) are advancing rapidly, equipping artificial intelligence (AI) agents with stronger reasoning and decision-making capacities. AI agents are moving from passive tools to more adaptive collaborators. However, the black-box nature and hallucinations of LLMs create uncertainties about their outputs, which may impact user trust in scenarios involving human-LLM collaboration and, in turn, lead to inconsistent outcomes in mixed-motive scenarios. To investigate how humans adjust their cooperation intentions in response to LLM unpredictability, we conducted repeated Prisoner’s Dilemma games with 30 participants (15 males, 15 females) interacting with LLM agents with different declared identities. Results revealed that an agent’s declared identity, the user’s gender, and their interaction influenced cooperation intentions. The semi-structured interviews further showed that these effects were mediated by gender differences in perceived agent identity and trustworthiness. By moving beyond the predominantly cooperative settings, this study uncovers robust interactions between agent identity and user gender in mixed-motive scenarios. These findings offer practical insights for developing more trustworthy AI systems for real-world problems.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103740"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Understanding trust toward human versus AI-generated health information through behavioral and physiological sensing","authors":"Xin Sun ,&nbsp;Rongjun Ma ,&nbsp;Shu Wei ,&nbsp;Pablo Cesar ,&nbsp;Jos A. Bosch ,&nbsp;Abdallah El Ali","doi":"10.1016/j.ijhcs.2025.103714","DOIUrl":"10.1016/j.ijhcs.2025.103714","url":null,"abstract":"<div><div>As AI-generated health information proliferates online and becomes increasingly indistinguishable from human-sourced information, it becomes critical to understand how people trust and label such content, especially when the information is inaccurate. We conducted two complementary studies: (1) a mixed-methods survey (N=142) employing a 2 (source: Human vs. LLM) <span><math><mo>×</mo></math></span> 2 (label: Human vs. AI) <span><math><mo>×</mo></math></span> 3 (type: General, Symptom, Treatment) design, and (2) a within-subjects lab study (N=40) incorporating eye-tracking and physiological sensing (ECG, EDA, skin temperature). Participants were presented with health information varying by source-label combinations and asked to rate their trust, while their gaze behavior and physiological signals were recorded. We found that LLM-generated information was trusted more than human-generated content, whereas information labeled as human was trusted more than that labeled as AI. Trust remained consistent across information types. Eye-tracking and physiological responses varied significantly by source and label. Machine learning models trained on these behavioral and physiological features predicted binary self-reported trust levels with 73 % accuracy and information source with 65 % accuracy. Our findings demonstrate that adding transparency labels to online health information modulates trust. Behavioral and physiological features show potential to verify trust perceptions and indicate if additional transparency is needed.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103714"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145980255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"What leads to better immersive experiences? The role of guidance and mobility in virtual reality museums","authors":"Elías Vega ,&nbsp;Carmen Camarero ,&nbsp;Juho Hamari ,&nbsp;Nannan Xi","doi":"10.1016/j.ijhcs.2026.103739","DOIUrl":"10.1016/j.ijhcs.2026.103739","url":null,"abstract":"<div><div>Virtual reality (VR) is reshaping tourism as museums increasingly adopt it to create immersive visitor experiences. While presence is key to VR effectiveness, little is known about how interaction modes affect it. This study examines the impact of two elements −guidance and spatial mobility− on perceived presence in virtual museum visits. It also explores the psychological mechanisms involved and identifies autonomy as a positive driver and satiation as a limiting factor. Results show that guidance enhances presence although it slightly reduces autonomy, while spatial mobility has less of an effect. In turn, presence boosts perceived entertainment and informativeness and positively influences attitudes toward the destination and visit intention. This research helps to understand how interaction design in immersive environments shapes user experience and behaviour. It offers theoretical insights on presence drivers as well as practical implications for creating more effective, satisfying, and wellbeing-oriented VR experiences in tourism.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103739"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust bias mitigation using dual contrastive learning based text style transfer","authors":"Osama Subhani Khan,&nbsp;Naima Iltaf,&nbsp;Usman Zia","doi":"10.1016/j.ijhcs.2026.103748","DOIUrl":"10.1016/j.ijhcs.2026.103748","url":null,"abstract":"<div><div>Text Style Transfer (TST) is a natural language processing (NLP) task involving the modification of textual style while upholding semantic content integrity. Current approaches mostly rely on the sentiment transfer task which involves modifying negative customer reviews to positive and vice versa. While this is important for evaluating the style modification and semantic consistency of TST systems, the application of such a task is questionable. TST has the potential to mitigate bias in real time comments. However, research in bias mitigation using TST is scarce in the literature. Current challenges faced by established frameworks include the maintenance of consistency and coherence when confronted with limited and noisy data especially when it comes to bias mitigation. Furthermore, performance is impeded by the scarcity of ample data necessary for data-driven AI frameworks. This research introduces a framework leveraging contrastive learning to transform dispersed input points into an embedding space. A triplet loss, augmented by an enhanced dual contrastive loss, is employed to distinguish between styles. We propose joint training of the masked language model with two dual contrastive style detectors and a sequence editor aimed at preserving content and modifying style simultaneously. Our model demonstrates a significant enhancement over existing baseline systems, attributing its success to the incorporation of dual contrastive learning with masked language modeling. Experimental results showcase the superior performance of the proposed system when compared to state-of-the-art models, as validated on two benchmark datasets through a series of experiments.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103748"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From movement to learning: Leveraging VR behavioral metrics to evaluate cognitive load and curiosity","authors":"Matisse Poupard ,&nbsp;Florian Larrue ,&nbsp;Martin Bertrand ,&nbsp;Dominique Liguoro ,&nbsp;Hélène Sauzéon ,&nbsp;André Tricot","doi":"10.1016/j.ijhcs.2026.103751","DOIUrl":"10.1016/j.ijhcs.2026.103751","url":null,"abstract":"<div><div>Virtual Reality (VR) is increasingly used in education due to its immersive and interactive capabilities, but its impact on cognitive load and curiosity remains underexplored, particularly regarding real-time behavioral indicators of cognitive load and curiosity. This study investigates how VR behavioral metrics, specifically hand and head movement patterns, can serve as objective, synchronous indicators of cognitive engagement and intrinsic motivation. A controlled experiment was conducted with 125 medical students, who engaged in a neuroanatomy learning task within a VR environment featuring varying levels of interactivity. Behavioral data, including movement entropy, exploration patterns, and gesture dynamics, were analyzed in relation to self-reported measures of cognitive load, motivation, and engagement. Results indicate that while greater hand movement was associated with lower intrinsic motivation, higher head movement correlated positively with germane cognitive load and intrinsic motivation, implying deeper cognitive engagement. Additionally, movement entropy emerged as a predictor of curiosity-driven learning, suggesting its potential as an indicator of learning behaviors in VR environments. These findings contribute to a better understanding of how behavioral data can complement traditional assessments of learning experiences in VR. They also highlight the need for further research into integrating movement-based metrics with instructional design to support engagement and learning.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103751"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards ecological validity when assessing ADHD symptoms: Patterns in automatically collected, real-world PC activity data","authors":"Matheus B. da Costa ,&nbsp;Elizabeth Chan ,&nbsp;Joshua Langberg ,&nbsp;Isabelle Cuber ,&nbsp;Fatemeh Jamalinabijan ,&nbsp;Aleksander Kurgan ,&nbsp;Thomas Fritz ,&nbsp;David C. Shepherd","doi":"10.1016/j.ijhcs.2025.103724","DOIUrl":"10.1016/j.ijhcs.2025.103724","url":null,"abstract":"<div><div>Neuropsychological tests assessing attention and executive function (EF) in individuals with ADHD demonstrate little to no association with real-world ratings of ADHD behaviors. To address this critical gap, this study developed metrics that can analyze automatically collected data to measure levels of attention, motivation, and effort in emerging adults with ADHD. Specifically, we used virtual reality to simulate a study space and collect in-the-moment computer activity data while university students with ADHD (N = 21; 38% female) engaged in 12 sessions (total 180 h) of real-world tasks. To identify common sequences we performed a qualitative analysis of this work session data (i.e., descriptive window titles, input levels, and window switches), resulting in four themes representing positive and negative work activity patterns. From these themes we derived four metrics, and a quantitative analysis showed that two predicted behavioral indices of attention, effort, and motivation with effects in the moderate range. To our knowledge, we are the first group to design and test such an approach, as well as validate identified computer metrics to behavioral indices of attention and EF. Given the automated nature of computer data collection and analysis, this approach represents a scalable, novel method for ADHD assessment and treatment.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103724"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design patterns of human-AI interfaces in healthcare","authors":"Rui Sheng ,&nbsp;Chuhan Shi ,&nbsp;Sobhan Lotfi ,&nbsp;Shiyi Liu ,&nbsp;Adam Perer ,&nbsp;Huamin Qu ,&nbsp;Furui Cheng","doi":"10.1016/j.ijhcs.2026.103737","DOIUrl":"10.1016/j.ijhcs.2026.103737","url":null,"abstract":"<div><div>Human–AI interfaces play a pivotal role in integrating clinicians’ expertise with artificial intelligence to enhance both healthcare practice and research. However, designing effective interfaces in this domain remains a significant challenge. The inherent complexity of medical data, the influence of domain-specific conventions, and the diverse needs of clinical users compound the challenge of developing practical and usable solutions. In this study, we review existing solutions and synthesize a set of design patterns—recurring approaches that support the design of human–AI interfaces in clinical settings. We conducted a comprehensive literature review of human–AI interaction designs in clinical contexts, through which we identified 15 information entities commonly presented to users and 12 design patterns used to organize and communicate this information effectively. For each design pattern, we summarize the underlying design problem, the proposed solution, and the rationale for when the pattern should or should not be applied, based on insights from both the literature and semi-structured interviews with 12 healthcare professionals. We evaluated the proposed design patterns through an online workshop involving 14 experienced UI designers. During the workshop, participants were asked to create interface sketches for healthcare-related scenarios drawn from their own professional experience, using our design patterns as guidance. Our findings show that the proposed design patterns helped participants ground their designs in user needs, generate a wider range of design alternatives, and simplify complex interface structures. We further analyzed and summarized the participants’ usage strategies and feedback regarding the applicability and usefulness of the design patterns. By consolidating recurring solutions and design rationales, our work provides a practical foundation for creating more efficient and clinically meaningful human–AI interfaces, ultimately advancing the integration of AI into real-world healthcare practice.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103737"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examining movement as foundation for embodied player experiences and technology relationships","authors":"Louise Petersen Matjeka ,&nbsp;Hanna Elina Wirman ,&nbsp;Beatrix Vereijken ,&nbsp;Florian 'Floyd' Mueller","doi":"10.1016/j.ijhcs.2026.103736","DOIUrl":"10.1016/j.ijhcs.2026.103736","url":null,"abstract":"<div><div>Game studies and Human-Computer Interaction (HCI) research on embodied experiences and technology relationships often diverge; while game studies focus on the player–in-game character relationship, HCI emphasises sensory perception and stimulation. This paper bridges these perspectives by examining movement as fundamental to perception and interaction, exploring how movement unfolds in sequences between player(s) and technologies. The paper presents a theoretical framework that combines the neuroscientific theories of predictive processing and active inference with phenomenology to understand perception as a subjective experience along with its underlying neurobiological processes. Complemented by an autoethnographic inquiry in which the primary author played seven games over three years, we apply the theoretical framework to analyse how movement drives embodied experiences. Our findings reveal that the composition of movement sequences is a key mechanism for embodied player experiences and technology relationships. Furthermore, the study identifies four dynamics in the sequential movement compositions that shape the qualities of experience. By foregrounding movement as central to connecting players and avatars in sensory engagement, we provide a unified perspective that benefits researchers and designers across the fields of game studies and HCI.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103736"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146038690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-generated personas: Representing user needs with generative AI models","authors":"Joni Salminen ,&nbsp;Lene Nielsen ,&nbsp;Ali Farooq ,&nbsp;Bernard J. Jansen","doi":"10.1016/j.ijhcs.2026.103745","DOIUrl":"10.1016/j.ijhcs.2026.103745","url":null,"abstract":"","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"209 ","pages":"Article 103745"},"PeriodicalIF":5.1,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146189560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}