International Journal of Human-Computer Studies最新文献

{"title":"User judgment of an AI model is biased by its description: A study in a job interview training context","authors":"Sharon Lynn Chu ,&nbsp;Marcin Karcz ,&nbsp;Amal Hashky ,&nbsp;Neha Rani ,&nbsp;Theodora Chaspari ,&nbsp;Winfred Arthur Jr. ,&nbsp;Eric D. Ragan","doi":"10.1016/j.ijhcs.2025.103691","DOIUrl":"10.1016/j.ijhcs.2025.103691","url":null,"abstract":"<div><div>The growth of artificial intelligence (AI) has introduced new AI-powered systems into many aspects of everyday life. Although many such systems may be embedded in contexts where long-term use is justified, there are also many cases where usage of such systems can be brief or limited to a single session. In those cases, initial information provided to the user about the AI model is important since users may not have enough engagement with the system to develop a mental model over time through use. Instead, users may simply rely on first impressions. However, little is known about how given information about the AI model in a system affects user judgment of the system. This work investigates this question within the context of job interview training. We conducted a controlled experiment where the description of the AI model within a simulated job interview training system was manipulated to describe the model as being either basic or more advanced. Participants in the condition where the AI model was described as more sophisticated and advanced reported significantly higher levels of agreement with the model outputs, more favorable ratings, and a greater willingness to use the system output.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103691"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145693558","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":"Toward AI-driven UI transition intuitiveness inspection for smartphone apps","authors":"Xiaozhu Hu ,&nbsp;Xiaoyu Mo ,&nbsp;Xiaofu Jin ,&nbsp;Yuan Chai ,&nbsp;Yongquan Hu ,&nbsp;Mingming Fan ,&nbsp;Tristan Braud","doi":"10.1016/j.ijhcs.2025.103661","DOIUrl":"10.1016/j.ijhcs.2025.103661","url":null,"abstract":"<div><div>Participant-involved formative evaluations is necessary to ensure the intuitiveness of UI transition in mobile apps, but they are neither scalable nor immediate. Recent advances in AI-driven user simulation show promise, but they have not specifically targeted this scenario. This work introduces UTP (UI Transition Predictor), a tool designed to facilitate formative evaluations of UI transitions through two key user simulation models: 1. Predicting and explaining potential user uncertainty during navigation. 2. Predicting the UI element users would most likely select to transition between screens and explaining the corresponding reasons. These models are built on a human-annotated dataset of UI transitions, comprising 140 UI screen pairs and encompassing both high-fidelity and low-fidelity counterparts of UI screen pairs. Technical evaluation indicates that the models outperform GPT-4o in predicting user uncertainty and achieve comparable performance in predicting users’ selection of UI elements for transitions using a lighter, open-weight model. The tool has been validated to support the rapid screening of design flaws, and the confirmation of UI transitions appears to be intuitive.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"206 ","pages":"Article 103661"},"PeriodicalIF":5.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145467866","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":"How do young users perceive and respond to AI-generated short-form videos? An exploration of Generation Z’s perceptions, emotional responses, and trust in AI-created video on social media platforms","authors":"Hoai Lan Duong,&nbsp;Thi Kim Oanh Vo","doi":"10.1016/j.ijhcs.2025.103660","DOIUrl":"10.1016/j.ijhcs.2025.103660","url":null,"abstract":"<div><div>As artificial intelligence (AI) becomes more prominent in shaping media experiences, short form video platforms such as TikTok, Instagram Reels, and YouTube Shorts have emerged as dynamic environments for complex interaction between humans and AI. While most research in human computer interaction has focused on AI in practical or task based roles, there is still limited understanding of how young people perceive and respond to AI-generated short-form videos in everyday digital contexts. This study helps fill that gap by focusing on Generation Z, the most active and influential demographic on social media, and the first to encounter generative AI as an integrated part of everyday digital life. Drawing on the Stimulus Organism Response model and Uncanny Valley Theory, and based on in-depth interviews, this study explores (1) how Gen Z perceives the human likeness and emotional authenticity of AI generated short form videos, and (2) what interactional and design features shape their trust and engagement. The findings reveal a mix of admiration and unease. Key design elements such as visuals, voice, storytelling, and transparency about authorship play a critical role in how young users assess authenticity and build trust. The study expands the scope of Human-Computer Interaction by treating AI as a social and creative presence. It introduces the Perceptual Response Zone to explain how emotional realism shapes user trust and proposes a new framework for understanding how design stimuli influence engagement behaviors. These insights offer practical guidance for creating emotionally resonant AI content for youth audiences.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"206 ","pages":"Article 103660"},"PeriodicalIF":5.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145374280","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":"Oh no! She is Flying! Interaction Analysis of Therapist-Robot Collaboration in Gait Rehabilitation","authors":"Jose Pablo De la Rosa Gutierrez ,&nbsp;Thiago Rocha Silva ,&nbsp;Anders Stengaard Sørensen ,&nbsp;Gitte Rasmussen","doi":"10.1016/j.ijhcs.2025.103620","DOIUrl":"10.1016/j.ijhcs.2025.103620","url":null,"abstract":"<div><div>Strokes are a leading cause of disability, with many survivors experiencing significant mobility impairments. While robot-assisted rehabilitation offers a promising solution, its adoption seems challenged by high upfront costs, low flexibility and complex configuration workflows. To address these challenges, this study conducts an interaction analysis to identify key requirements for empowering therapists to self-configure and adapt a flexible, cost-effective robot during gait rehabilitation tasks. Our analysis is based on 20 training sequences from a 60-hour video dataset collected across three experimental setups, involving young adults with motor impairments training with the assistance of the robot. Drawing methods from Ethnomethodology and Conversation Analysis (EMCA), we examined the sequential organization of actions between technology, therapist and participant, identifying three main stages: setup, training, and completion. During setup, coordinated actions prepare the participant and the robot for the main training task; during training, participant and robot engage in movement while the therapist iterates adjustments; and in completion, coordinated actions prepare the participant for transitioning back to their conventional support system. Our analysis highlights some requirements and strategies for developing End-User Development (EUD) environments for robot-assisted physiotherapy, emphasizing user-driven workflows, multimodal transitions between robot’s assistance modes, and real-time robotic feedback that maintains coherence with therapists’ practices.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"206 ","pages":"Article 103620"},"PeriodicalIF":5.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145420527","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":"Mimicking fruit textures with low-cost stylus interfaces for accessible sensory interaction","authors":"Christian Gonzalez ,&nbsp;Luis M. Zamudio ,&nbsp;Jesus Favela ,&nbsp;Monica Tentori","doi":"10.1016/j.ijhcs.2025.103659","DOIUrl":"10.1016/j.ijhcs.2025.103659","url":null,"abstract":"<div><div>Replicating real-world textures using haptic technology poses significant challenges, particularly in accurately capturing complex tactile qualities such as smoothness, roughness, and sharpness through vibration-based information. This research investigates how vibration parameters, intensity, duration, and off-time, can be manipulated to simulate textures inspired by fruit skins, including smooth-apple, rough-melon, bumpy-corn, sharp-pineapple, and adhesive-banana. Using a user-centered design methodology, we developed five vibrotactile patterns and implemented them within the Cactus Mobile Haptic Interface. The patterns were delivered via two interaction devices, a thimble and a stylus pen, designed to enable touch-based activities and tactile experiences. An empirical study with 36 participants evaluated those devices within three tasks: Tolerance to 10-second exposures, change perception, and the ability to associate patterns with real-world textures. Results showed that most patterns were accurately classified (76% with the thimble and 78% the stylus), although the adhesive texture proved more difficult to identify. Rough and sharp textures received slightly lower comfort ratings. While there were notable confusions between similar patterns, such as the sharp–bumpy pair, the type of interaction device did not significantly affect classification accuracy. These findings highlight the potential of low-cost haptic interfaces to mimic sensations from natural, realistic textures and emphasize the importance of refining vibration design for improved perceptual clarity. This work contributes to the development of accessible, portable, and customizable haptic systems designed for sensory interaction in therapeutic, educational, and interactive environments. Future research will focus on refining ambiguous patterns and exploring sensory integration to expand the system’s usability in tactile therapy.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"206 ","pages":"Article 103659"},"PeriodicalIF":5.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145420528","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":"Does the peak-end rule apply to judgments of body ownership in virtual reality?","authors":"Wen-Jie Tseng ,&nbsp;Kasper Hornbæk","doi":"10.1016/j.ijhcs.2025.103662","DOIUrl":"10.1016/j.ijhcs.2025.103662","url":null,"abstract":"<div><div>While body ownership is central to research in virtual reality (VR), it remains unclear how experiencing an avatar over time shapes a person’s summary judgment of it. Such a judgment could be a simple average of the bodily experience, or it could follow the peak-end rule, which suggests that people’s retrospective judgment correlates with the most intense and recent moments in their experiencing. We systematically manipulate body ownership over a three-minute avatar embodiment using visuomotor asynchrony. Asynchrony here serves to negatively influence body ownership. We conducted one lab study (<span><math><mrow><mi>N</mi><mo>=</mo><mn>28</mn></mrow></math></span>) and two online studies (pilot: <span><math><mrow><mi>N</mi><mo>=</mo><mn>97</mn></mrow></math></span> and formal: <span><math><mrow><mi>N</mi><mo>=</mo><mn>128</mn></mrow></math></span>) to investigate the influence of visuomotor asynchrony given (1) order, meaning early or late, (2) duration and magnitude while controlling the order, and (3) the interaction between order and magnitude. Our results indicate a significant order effect — later visuomotor asynchrony decreased the rating of body-ownership judgments more — but no convergent evidence on magnitude. We discuss how body-ownership judgments may be formed sensorily or affectively.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"206 ","pages":"Article 103662"},"PeriodicalIF":5.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145467865","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":"f-RecX: A framework for designing effective textual explanations in recommender systems’ user interfaces","authors":"Ibrahim Al-Hazwani ,&nbsp;Gabriela Morgenshtern ,&nbsp;Mennatallah El-Assady ,&nbsp;Jürgen Bernard","doi":"10.1016/j.ijhcs.2025.103627","DOIUrl":"10.1016/j.ijhcs.2025.103627","url":null,"abstract":"<div><div>Recommender systems (RecSys) have become ubiquitous in users’ daily digital interactions, significantly influencing decision-making processes. As these systems grow in algorithmic complexity, effective explanations for non-expert users become essential to fostering understanding and trust. While academic research explores diverse explanation methods, commercial applications predominantly employ textual explanations due to their implementation efficiency and user familiarity. However, the effectiveness of these textual explanations is often compromised by suboptimal presentation within RecSys user interfaces (UIs), leading to reduced user engagement and comprehension. This issue is particularly relevant given the recent emergence of large language models (LLMs) for generating RecSys explanations. We introduce f-RecX, a conceptual framework for characterizing and designing effective textual explanations in RecSys UIs. Based on a two-phase methodology combining qualitative user studies and quantitative evaluations, f-RecX maps four input dimensions (Explanation Style, Goals, Domain Dynamics, and Recommender Systems Technique) to an output dimension focused on visual representation. The framework aims to enhance the ’consumability’ of textual explanations by making them easier to locate and comprehend, and more valuable for non-expert users. We demonstrate f-RecX’s applicability through a usage scenario and analysis of existing RecSys UIs, offering valuable insights for enhancing explainability and user experience.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"205 ","pages":"Article 103627"},"PeriodicalIF":5.1,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159549","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":"Avatars in mixed-reality meetings: A longitudinal field study of realistic versus cartoon facial likeness effects on communication, task satisfaction, presence, and emotional perception","authors":"Georgiana Cristina Dobre ,&nbsp;Marta Wilczkowiak ,&nbsp;Marco Gillies ,&nbsp;Xueni Pan ,&nbsp;Sean Rintel","doi":"10.1016/j.ijhcs.2025.103632","DOIUrl":"10.1016/j.ijhcs.2025.103632","url":null,"abstract":"<div><div>We conducted a within-subjects study to examine how realistic faces and cartoon faces on avatars affect communication, task satisfaction, sense of presence, and mood perception in mixed reality meetings. Over the course of two weeks, six groups of co-workers (14 people) held recurring meetings using Microsoft HoloLens2 devices, each person embodying a personal full-body avatar with either a realistic face or cartoon face. Half of the groups started with the realistic face avatar and switched to the cartoon face version halfway through (RC condition), and the other half with the cartoon-face avatar first (CR condition). Results showed that participants in the RC condition may have had higher expectations and more errors in perceiving their colleagues’ moods. Participants in the CR condition reported that the avatars’ appearance mattered less over time and experienced increased comfort and improved identification of their colleagues. Participants rated words, tone of voice, and movement as the most useful cues for perceiving colleagues’ moods, regardless of avatar rendering style. In the RC condition, participants rated gaze as more useful than facial expressions, while in the CR condition, both gaze and facial expressions were rated as the least useful. Results also suggested that participants had more errors when perceiving negative moods in their colleagues, with this trend appearing for most moods, but depending on conditions. Implications of these findings for mixed and virtual reality meetings are discussed. This work contributes to the field of remote collaboration by providing insights from longitudinal data on the impact of avatar appearance on various aspects of work meetings in virtual environments.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"205 ","pages":"Article 103632"},"PeriodicalIF":5.1,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222124","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":"Conversational agents and charitable behavioral intentions: The roles of modality, communication style, and perceived anthropomorphism","authors":"Junqi Shao ,&nbsp;Leona Yi-Fan Su ,&nbsp;Ziyang Gong ,&nbsp;Minrui Chen","doi":"10.1016/j.ijhcs.2025.103616","DOIUrl":"10.1016/j.ijhcs.2025.103616","url":null,"abstract":"<div><div>Conversational agents (CAs) are increasingly utilized by organizations for fundraising and volunteer recruitment. Yet, little is understood about how voice-based CAs could serve these purposes optimally. This experimental study therefore compares voice-based CAs against text-based ones in terms of their ability to foster users’ intentions to make charitable contributions, and investigates the potential mediation of such effects by two dimensions of user-perceived anthropomorphism. Additionally, it examines how a CA’s communication style moderates these effects. It found that, when a voice-based CA employed a formal communication style, mindless anthropomorphism was a significant mediator of its positive association with charitable behavioral intentions. Conversely, when employing an informal communication style, a text-based CA elicited significantly higher levels of mindful anthropomorphism, and also was positively linked to charitable behavioral intentions. These findings expand our theoretical understanding of how CA modalities influence people’s moral responses toward computers; how this effect could be impaired, or strengthened, by different communication styles; and the underlying mechanisms of two dimensions of anthropomorphism. Practical implications are also discussed.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"205 ","pages":"Article 103616"},"PeriodicalIF":5.1,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050577","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 the future of pedestrian–AV interaction: Human perception vs. LLM insights on Smart Pole Interaction Unit in shared spaces","authors":"Vishal Chauhan ,&nbsp;Anubhav ,&nbsp;Chia-Ming Chang ,&nbsp;Xiang Su ,&nbsp;Jin Nakazato ,&nbsp;Ehsan Javanmardi ,&nbsp;Alex Orsholits ,&nbsp;Takeo Igarashi ,&nbsp;Kantaro Fujiwara ,&nbsp;Manabu Tsukada","doi":"10.1016/j.ijhcs.2025.103628","DOIUrl":"10.1016/j.ijhcs.2025.103628","url":null,"abstract":"<div><div>As autonomous vehicles (AVs) reshape urban mobility, establishing effective communication between pedestrians and self-driving vehicles has become a critical safety imperative. This work investigates the integration of Smart Pole Interaction Units (SPIUs) as external human–machine interfaces (eHMIs) in shared spaces and introduces an innovative approach to enhance pedestrian–AV interactions. To provide subjective evidence on SPIU usability, we conduct a group design study (“Humans”) involving 25 participants (aged 18–40). We evaluate user preferences and interaction patterns using group discussion materials, revealing that 90% of the participants strongly prefer real-time multi-AV interactions facilitated by SPIU over conventional eHMI systems, where a pedestrian must look at multiple AVs individually. Furthermore, they emphasize inclusive design through multi-sensory communication channels—visual, auditory, and tactile signals—specifically addressing the needs of vulnerable road users (VRUs), including those with impairments. To complement these non-expert, real-world insights, we employ three leading Large Language Models (LLMs) (ChatGPT-4, Gemini-Pro, and Claude 3.5 Sonnet) as “experts” due to their extensive training data. Using the advantages of the multimodal vision-language processing capabilities of these LLMs, identical questions (text and images) used in human discussions are posed to generate text responses for pedestrian–AV interaction scenarios. Responses generated from LLMs and recorded conversations from human group discussions are used to extract the most frequent words. A keyword frequency analysis from both humans and LLMs is performed with three categories, Context, Safety, and Important. Our findings indicate that LLMs employ safety-related keywords 30% more frequently than human participants, suggesting a more structured, safety-centric approach. Among LLMs, ChatGPT-4 demonstrates superior response latency, Claude shows a closer alignment with human responses, and Gemini-Pro provides structured and contextually relevant insights. Our results from “Humans” and “LLMs” establish SPIU as a promising system for facilitating trust-building and safety-ensuring interactions among pedestrians, AVs, and delivery robots. Integrating diverse stakeholder feedback, we propose a prototype SPIU design to advance pedestrian–AV interactions in shared urban spaces, positioning SPIU as crucial infrastructure hubs for safe and trustworthy navigation.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"205 ","pages":"Article 103628"},"PeriodicalIF":5.1,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057275","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}