International Journal of Human-Computer Studies最新文献

{"title":"Unraveling multiparty conversations: From human interaction mechanisms to conversational agent challenges and persona design","authors":"Shitao Fang ,&nbsp;Xingyu Liu ,&nbsp;Takeo Igarashi ,&nbsp;Koji Yatani","doi":"10.1016/j.ijhcs.2025.103719","DOIUrl":"10.1016/j.ijhcs.2025.103719","url":null,"abstract":"<div><div>Multiparty conversations are ubiquitous and indispensable in diverse social and collaborative contexts. However, current conversational agents (CAs) face significant challenges in effectively engaging in such interactions, particularly within text-based environments. While earlier limitations were often attributed to the inadequacies of AI models, recent advances in large language models now compel us to revisit both our understanding of multiparty conversation and the way we design CAs. This paper synthesizes findings from two complementary qualitative investigations and proposes a conceptual model for designing CAs that can genuinely participate, rather than merely function as tools or outsiders. The first study, employing retrospective think-aloud sessions (N=30) with users in text-based multiparty settings, uncovers 5 key interactional mechanisms (e.g., Turn-taking Management, Presence Management) that underpin successful human-human multiparty interactions, derived from participants’ articulated perceptions and reasoning. Subsequently, the second study, through semi-structured interviews (N=15), identifies user expectations for CA integration and key traits (e.g., proactivity, social authenticity) that shape an ideal CA persona perceived by users as a genuine participant. Drawing from these human-centric insights, we then derive design considerations, aiming to guide the development of CAs capable of more natural, effective, and socially intelligent participation in multiparty conversation.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103719"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883889","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":"MusicTraces: Combining music and painting to support adults with neurodevelopmental conditions and intellectual disabilities","authors":"Valentin Bauer ,&nbsp;Giacomo Caslini ,&nbsp;Marco Mores ,&nbsp;Mattia Gianotti ,&nbsp;Franca Garzotto","doi":"10.1016/j.ijhcs.2025.103675","DOIUrl":"10.1016/j.ijhcs.2025.103675","url":null,"abstract":"<div><div>People with NeuroDevelopmental Conditions (NDC) and associated Intellectual Disability (ID) often face social and emotional issues affecting their well-being. Although art therapies like music-making or painting can be beneficial, they often lack adaptability for those with moderate-to-severe ID or limited language abilities. Multisensory creative technologies combining art practices offer promising solutions but remain under-explored. This research investigates the impact of integrating music-making and painting within an interactive multisensory environment to support social communication, emotional regulation, and well-being in adults with moderate-to-severe NDCs and ID. The two-player music and painting activity called <em>MusicTraces</em> was first created through co-design process involving caregivers and people with NDCs and ID. Two field studies were conducted. The first study compared <em>MusicTraces</em> with traditional group painting with music for ten adults, while the second examined its impact over two sessions on eight adults with more severe conditions. Both studies showed improved social communication, social regulation and well-being. Insights are discussed to enhance collaboration between people with NDCs and ID through interactive creative technologies.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"207 ","pages":"Article 103675"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529163","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":"Creating text-based AI clones of myself: Exploring perceptions, development strategies, and challenges","authors":"Donggun Lee ,&nbsp;Suyoun Lee ,&nbsp;Hyunseung Lim,&nbsp;Hwajung Hong","doi":"10.1016/j.ijhcs.2025.103692","DOIUrl":"10.1016/j.ijhcs.2025.103692","url":null,"abstract":"<div><div>AI clones are evolving to include digital representations of real world individuals as chatbots. While often used to replicate famous figures, as the technology becomes more accessible, it is crucial to understand whether everyday users would create their own clones and how they interact with them. In this study, within the scope of AI-generated personas and their role in representing users’ needs and identities, we focus on personas that directly reflect the qualities of real humans. We define this as AI self clones—conversational AI representations that reflect their human creators—and examine how creators construct and engage with them. We conducted a 7-day study in which participants (N=12) created and interacted with their text based AI self clones using <span>CloneBuilder</span>, a web-based authoring interface for configuring and tuning AI self clones. The system enables individuals to create AI representations that encapsulate their unique personality, values, and interaction style. Our findings reveal that each participant developed a clone tailored to their personal circumstances. As the participants iteratively refined and tested their clone, their direction and expectations of AI clones evolved from performing specific roles to becoming entities that facilitated self exploration and relationship formation. Unexpected responses from the clone prompted self reflection and identity questioning. Overall, this paper explores the motivations for creating these clones, the strategies participants use to build and refine them, and the moments of emotional connection and break out experiences that emerge during the crafting process, along with key design implications, challenges, and ethical considerations in developing AI self clones.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103692"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145624449","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":"A music recommendation system for constructed music-evoked episodic memories (CoMEEMs)","authors":"Paul Raingeard de la Bletiere ,&nbsp;Mark Neerincx ,&nbsp;Rebecca Schaefer ,&nbsp;Catharine Oertel","doi":"10.1016/j.ijhcs.2025.103717","DOIUrl":"10.1016/j.ijhcs.2025.103717","url":null,"abstract":"<div><div>Music is widely used in human–computer interaction (HCI) to enhance engagement, sustain attention, and support cognitive stimulation. Yet its potential for deliberate mood regulation, particularly through personalized memory recall, remains largely unexplored.</div><div>Music-evoked autobiographical memories (MEAMs) are often elicited by well-known, favorite songs, yielding stronger mood effects than music without personal memory associations. However, songs can also trigger distressing memories, and will never capture all positive personal memories. Since happy personal memories can enhance mood, broader methods for retrieval are needed.</div><div>To address this, we introduce Constructed Music-Evoked Episodic Memories (CoMEEMs), a framework linking chosen episodic memories to music. By creating a personalized song-memory database, CoMEEMs enable autonomous mood regulation and communication in interactive systems, integrating memory cues—such as people and places—alongside mood congruence, to help choose songs with high mood regulatory impact.</div><div>In an experiment with 71 Dutch and French adults, participants described 87 positive memories and received song recommendations based on associated people and places, with and without mood matching. Results showed that song familiarity and genre were the strongest predictors of perceived fit, while valence, arousal, tempo, and lyrics played smaller roles. Mood congruence, especially in valence, significantly influenced song relevance. Participants emphasized the need for user input on emotional states and memory context. Based on these findings, we propose design guidelines to improve future music recommendation systems targeting memories.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103717"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840207","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":"Easy to handle: Exploring users’ interactions with an augmented reality human-machine interface for virtual stops in automated on-demand mobility scenarios","authors":"Fabian Hub ,&nbsp;Marc Wilbrink ,&nbsp;Michael Oehl","doi":"10.1016/j.ijhcs.2025.103671","DOIUrl":"10.1016/j.ijhcs.2025.103671","url":null,"abstract":"<div><div>For the success of future shared automated mobility on-demand (SAMOD) a high quality of service needs to be assured. One key challenge lies in the passenger journey, particularly in finding the designated virtual stop (vStop) for pick-up and identifying the approaching shuttle. Therefore, the new vStop human-machine interface (vStop HMI) concept supports passengers with means of augmented reality (AR). This explorative user study with young adults (<em>N</em> = 44) used a virtual reality (VR) setup to simulate the AR-based vStop HMI and answers two research questions across two consecutive scenarios: (1) When using an AR-based navigation aid like the vStop HMI, users tend to focus heavily on their device while walking, which may increase the risk of negligent roadside behavior. While restricting AR information access during walking might reduce this risk, how does it affect overall user experience? To examine this, we compared a vStop HMI with restricted AR information access against a baseline condition. Results showed positive effects on user experience and acceptance for both HMI versions, although workload was partly negatively affected. (2) When identifying the approaching shuttle, does using the vStop HMI effectively assist users in doing so and lead to positive user experience? Usability testing indicated positive rates of workload, user experience, and acceptance during the shuttle identification task. Overall, the findings suggest that selectively restricting AR information during navigation tasks can help mitigate undesired user behavior in roadside environments while maintaining high levels of pragmatic quality and acceptance. Moreover, the vStop HMI enables seamless shuttle identification, even under complex conditions. By improving these critical stages of the passenger journey, the vStop HMI concept has the potential to enhance the overall quality of SAMOD services and increase public acceptance of future shared, automated, demand-responsive transportation systems.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"207 ","pages":"Article 103671"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529164","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":"SnapSound: Empowering everyone to customize sound experience with Generative AI","authors":"Jiyeon Oh,&nbsp;Jin-Woo Jeong","doi":"10.1016/j.ijhcs.2025.103673","DOIUrl":"10.1016/j.ijhcs.2025.103673","url":null,"abstract":"<div><div>The rise of user-centric experiences in the digital landscape has led to a surge in demand for personalized multimedia content. Users now seek to customize not only visual but also auditory components to suit their preferences. In this context, sound design plays a crucial role, enabling users to tailor audio experiences accordingly. However, its inherent complexity poses various challenges, particularly for non-expert users. To address this challenge, we introduce SnapSound, a novel assistive system designed specifically for non-experts in sound design for video content. Our system leverages generative AI to streamline the sound design process and offers intuitive tools for sound selection, synchronization, and seamless integration with visuals. Through a user study, we evaluate SnapSound’s usability and effectiveness compared to manual editing. Furthermore, our study provides valuable insights and design recommendations for enhancing user experience of future AI-based sound design systems. This work represents a significant step forward in empowering non-experts to easily customize their auditory experiences.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"207 ","pages":"Article 103673"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529192","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":"Ensuring provider fairness in recommender systems across coarse- and fine-grained groups","authors":"Elizabeth Gómez ,&nbsp;David Contreras ,&nbsp;Ludovico Boratto ,&nbsp;Maria Salamó","doi":"10.1016/j.ijhcs.2025.103688","DOIUrl":"10.1016/j.ijhcs.2025.103688","url":null,"abstract":"<div><div>The goal of provider fairness in recommender systems is to ensure equity by suggesting products from diverse providers or provider groups. When group fairness is among the goals of a system, coarse groups are frequently used, since there are typically few provider groups (e.g., two genders, or three/four age groups) and the number of items per group is large. Practically speaking, having fewer groups makes it easier for a platform to oversee how equity is distributed among them. Nevertheless, there are sensitive attributes, such as the age or the geographic provenance of the providers, that can be characterized at a fine granularity (e.g., one might group providers at the country level, instead of the continent one), which increases the number of groups and decreases the number of items per group. This study reveals that state-of-the-art models often fail to adequately recommend fine-grained provider groups when only coarse-grained groups are considered. This oversight can result in a fairness approach that, while adequate for broader demographic groups, neglects the needs of smaller subgroups. To address this disparity, we introduce CONFIGRE (COarse aNd FIne GRained Equity), an approach designed to balance equity across both coarse and fine-grained provider groups. Our methodology ensures that fairness is not only maintained at a broad demographic level but is also extended to more precisely defined groups, offering a more nuanced and comprehensive equity management in recommender systems.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103688"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145693557","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":"User personas, ideation and large language models: A post-hoc study","authors":"Stefano De Paoli","doi":"10.1016/j.ijhcs.2025.103690","DOIUrl":"10.1016/j.ijhcs.2025.103690","url":null,"abstract":"<div><div>Covering the full ideation of design with Large Language Models (LLMs) and user interview data remains an underexplored area in the current scholarship. This paper begins to address this gap and investigates the integration of LLMs in a user-centered design process, creating user personas based on qualitative interview data. This work further explores using these personas for deriving scenarios, and functionality requirements, also with LLMs. First, LLMs are used to identify key themes of users from interviews, subsequently synthesising these into personas. Second, personas are expanded into scenarios and associated functionalities for a digital platform, simulating the ideation phase of a design process. The findings illustrate how LLMs can potentially streamline these early design stages. An evaluation shows that the process discovers a list of functionalities which are, to a reasonable extent, comparable to those that human researchers have produced separately.</div><div>The study proposes a practical procedure for integrating LLMs into qualitative design ideation workflows. The dataset used comprises 26 Open Access interviews from a previous Horizon project, from which eight personas and related scenarios are derived. To support further experimentation and practical applications, several computational resources used in performing analysis and generating LLM-based personas are shared. This enables reproducibility and encourages broader exploration of LLM-assisted design ideation.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103690"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145555375","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":"Pika: Designing a social-support agent to improve drivers’ experience in gig work","authors":"Wei Xiang ,&nbsp;Xinli Chen ,&nbsp;Tianhui Guo ,&nbsp;Min Zhou ,&nbsp;Shi Chen","doi":"10.1016/j.ijhcs.2025.103721","DOIUrl":"10.1016/j.ijhcs.2025.103721","url":null,"abstract":"<div><div>Drivers in gig work face a steady stream of demanding tasks, with the interaction between agents and workers playing a significant role in drivers’ performance. However, there has been limited exploration of challenges and opportunities in these interactions. This paper introduces social support in conversational agents to improve human-agent interaction within driving gigs. We began by conducting semi-structured interviews with 20 driving workers to uncover interaction challenges and strategies they employ. Building upon these insights, we designed Pika, a conversational agent offering both informational and emotional support. A two-stage empirical study involving 59 driving workers demonstrated the benefits of Pika in improving work performance and user experience. Our work calls for a focus on equitable collaborative relationships to enhance work efficiency and well-being in gig work.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"208 ","pages":"Article 103721"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883888","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":"LLM-powered assistant with electrotactile feedback to assist blind and low vision people with maps and routes preview","authors":"Chutian Jiang ,&nbsp;Yinan Fan ,&nbsp;Junan Xie ,&nbsp;Emily Kuang ,&nbsp;Kaihao Zhang ,&nbsp;Mingming Fan","doi":"10.1016/j.ijhcs.2025.103682","DOIUrl":"10.1016/j.ijhcs.2025.103682","url":null,"abstract":"<div><div>Previewing routes to unfamiliar destinations is a crucial task for many blind and low vision (BLV) individuals to ensure safety and confidence before their journey. While prior work has primarily supported navigation during travel, less research has focused on how best to assist BLV people in previewing routes on a map. We designed a novel electrotactile system around the fingertip and the Trip Preview Assistant (TPA) to convey map elements, route conditions, and trajectories. TPA harnesses large language models (LLMs) to dynamically control and personalize electrotactile feedback, enhancing the interpretability of complex spatial map data for BLV users. In a user study with twelve BLV participants, our system demonstrated improvements in efficiency and user experience for previewing maps and routes. This work contributes to advancing the accessibility of visual map information for BLV users when previewing trips.</div></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":"207 ","pages":"Article 103682"},"PeriodicalIF":5.1,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529165","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}