Operationalizing Perceptions of Agent Gender: Foundations and GuidelinesThe “gender” of intelligent agents, virtual characters, social robots, and other agentic machines has emerged as a fundamental topic in studies of people's interactions with computers. Perceptions of agent gender can help explain user attitudes and behaviours—from preferences to toxicity to stereotyping—across a variety of systems and contexts of use. Yet, standards in capturing perceptions of agent gender do not exist. A scoping review was conducted to clarify how agent gender has been operationalized—labelled, defined, and measured—as a perceptual variable. One-third of studies manipulated but did not measure agent gender. Norms in operationalizations remain obscure, limiting comprehension of results, congruity in measurement, and comparability for meta-analyses. The dominance of the gender binary model and latent anthropocentrism have placed arbitrary limits on knowledge generation and reified the status quo. We contribute a systematically-developed and theory-driven meta-level framework that offers operational clarity and practical guidance for greater rigour and inclusivity.2026KSKatie Seaborn et al.Institute of Science TokyoAgent Personality & AnthropomorphismGender & Race Issues in HCITechnology Ethics & Critical HCICHI
Hi, how do I human this: Neurodiversity-Affirming Design for Autistic Adults' Formation of IdentityHuman-Computer Interaction (HCI) has been critiqued for grounding technologies for disabled people in ableist paradigms, where the emphasis is placed on `fixing' autism rather than supporting autistic people. In contrast, the neurodiversity paradigm has helped many autistic people to develop an autistic identity, foster greater self-esteem, and build a sense of belonging within the broader neurodiversity community. Yet, little is known about how digital technologies might support information-seeking and self-reflection practices that contribute to autistic identity formation. Most HCI literature has largely focused on children, and has overlooked the experiences of autistic adults with intersecting gender and ethnic identities. This study addresses that gap by reporting findings from a survey (N=21) and participatory design workshops (n=8), where autistic cis and transgender women, as well as non-binary adults, reflected on their journeys towards identifying as autistic following a late autism diagnosis, and evaluated a prototype conversational agent designed to support this process. Our findings highlight the value of compassionate participatory design practices and contribute guidelines for designing agents that can support autistic adults and their identity formation.2026MSMaría Paula Silva et al.University College DublinCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Agent Personality & AnthropomorphismConversational ChatbotsCHI
Emulating Aggregate Human Choice Behavior and Biases with GPT Conversational AgentsCognitive biases often shape human decisions. While large language models (LLMs) have been shown to reproduce well-known biases, a more critical question is whether LLMs can predict biases at the individual level and emulate the dynamics of biased human behavior when contextual factors, such as cognitive load, interact with these biases. We adapted three well-established decision scenarios into a conversational setting and conducted a human experiment (N=1100). Participants engaged with a chatbot that facilitates decision-making through simple or complex dialogues. Results revealed robust biases. To evaluate how LLMs emulate human decision-making under similar interactive conditions, we used participant demographics and dialogue transcripts to simulate these conditions with LLMs based on GPT-4 and GPT-5. The LLMs reproduced human biases with precision. We found notable differences between models in how they aligned human behavior. This has important implications for designing and evaluating adaptive, bias-aware LLM-based AI systems in interactive contexts.2026SPStephen Pilli et al.University College DublinHuman-LLM CollaborationExplainable AI (XAI)AI-Assisted Decision-Making & AutomationCHI
Technology in Abortion Care: a Scoping Review on Contexts of Use, Research Methods, Ethical Considerations and ImpactGlobally, about 40% of women and people assigned female at birth live under laws that restrict or prohibit access to safe abortion care. Even where abortion is legal, socio-cultural stigma and health inequities hinder timely, equitable access. Technologies have been developed to support abortion seekers and providers in overcoming barriers to information, safe abortion care, and support. However, research on abortion care technologies is fragmented, spanning medical and computing publications, and lacking a consolidated understanding. To address this gap, we conducted a scoping review of 92 studies, examining technological applications, contexts of use, research methods, ethical considerations, and pathways to impact. This analysis informs the HCI research agenda for abortion care, highlighting future directions, and fostering reflection on design, ethics, and meaningful impact. We call on HCI researchers to move beyond telemedicine and U.S.-centric perspectives, re-politicize abortion care technologies, and consider temporality in delivering timely abortion care amid broader sociopolitical constraints.2026CNCamille Nadal et al.University College DublinMental Health Apps & Online Support CommunitiesAI Ethics, Fairness & AccountabilityTechnology Ethics & Critical HCICHI
Help me and I’ll help you: Speakers’ and listeners’ collaborative effort and the division of labour in human-agent collaborative communicationCollaboration is a key use case for conversational AI agents. Yet we know little about how agents' collaborative effort affects users' reciprocal effort and how this relates to perceptions of agent conversational capability. Through an online director-matcher task (n = 267) whereby participants interacted with agents that varied in their collaborative effort, we found that users rated agents that were less communicatively collaborative as less competent partners. Yet, contrary to the division of labour principle in communication, users only increased their own collaborative effort as speakers when communicating with more collaborative agents, whilst also benefitting more as listeners when interacting with such agents. We discuss the implications of these findings bringing together partner modelling and division of labour principles in driving human-agent collaborative communication in both speaker and listener effort, and consider the strategic application of agent collaborative effort in the design of conversational AI.2026PPPaola Raquel Peña et al.University College DublinConversational ChatbotsAgent Personality & AnthropomorphismHuman-LLM CollaborationCHI
Beyond the Illusion: LLMs and the Case for Pragmatic Cues in ConversationConversational agents are becoming increasingly adept at interacting with humans in a very natural manner. They incorporate subtle linguistic and paralinguistic cues: changes in tone and style, emotional expressions, or fillers like `mm-hm'. In human communication, such cues serve pragmatic functions that support mutual understanding and communicative success. This raises the question: do we want conversational agents to blindly mimic these cues, or can we use them more purposefully to serve a communicative function? We argue that the role of pragmatic cues in interaction with conversational user interfaces remains underexplored. A deeper understanding of how to strategically use them in appropriate contexts and their impact on human-machine interactions is crucial to enhance mutual understanding in conversations with artificial agents. Through this provocation, we propose a research agenda to spark discussion on how future research can address this.2025LSLaura Spillner et al.Agent Personality & AnthropomorphismHuman-LLM CollaborationCUI
The Benefits and Risks of LLMs for Facilitating Medical Decision-Making Among LaypersonsWe explored the potential of Large Language Models (LLMs) to facilitate laypersons' selection of treatment goals within a complex medical decision-making context. Using ChatGPT-4o, we developed an LLM-enhanced tool to guide users through goal elicitation, clarification, and revision. Our findings demonstrate that LLM features can effectively support these key aspects of decision-making. However, the absence of human interaction, the lack of patient- and context-specific treatment information, and the risk of information overload due to unconstrained access to LLM-generated content present significant risks. To balance the benefits and risks, we propose that LLM-enhanced facilitation tools for asynchronous, independent use should be clinician-initiated, constrain broad information search, and focus on creating a safe space for the exploration of laypersons' preferences and goals regarding the difficult challenges in balancing treatment and tradeoffs for quality of life.2025CFCharisse Foo et al.Human-LLM CollaborationAI-Assisted Decision-Making & AutomationDIS
Queer Joy on Social Media: Exploring the Expression and Facilitation of Queer Joy in Online PlatformsQueer Joy is conceptualised as a form of resistance to oppression by celebrating queerness in the face of adversity. This research aimed to centre queer joy and understand how it is expressed and may be facilitated in online spaces. To do this we conducted a survey with 100 UK participants who indicated they identified as LGBTQ+ on the online recruitment platform Prolific. We asked a series of open and closed questions in an online survey to investigate 1) what queer joy looks like on social media 2) how queer joy content is engaged with on social media 3) which platforms are perceived to facilitate queer joy and 4) how queer people protect their privacy online. The results suggested that to facilitate queer joy online, platforms should allow flexible self expression and community engagement, while allowing for granular control over privacy and the audience such content is shown to.2025MSMadeleine Steeds et al.University College Dublin, School of Information and Communication StudiesSocial Platform Design & User BehaviorGender & Race Issues in HCILGBTQ+ Community Technology DesignCHI
Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-ReferentsConversational agents that mimic people have raised questions about the ethics of anthropomorphizing machines with human social identity cues. Critics have also questioned assumptions of identity neutrality in humanlike agents. Recent work has revealed that intersectional Japanese pronouns can elicit complex and sometimes evasive impressions of agent identity. Yet, the role of other ``neutral'' non-pronominal self-referents (NPSR) and voice as a socially expressive medium remains unexplored. In a crowdsourcing study, Japanese participants (N=204) evaluated three ChatGPT voices (Juniper, Breeze, and Ember) using seven self-referents. We found strong evidence of voice gendering alongside the potential of intersectional self-referents to evade gendering, i.e., ambiguity through neutrality and elusiveness. Notably, perceptions of age and formality intersected with gendering as per sociolinguistic theories, especially ぼく (boku) and わたくし (watakushi). This work provides a nuanced take on agent identity perceptions and champions intersectional and culturally-sensitive work on voice agents.2025TFTakao Fujii et al.Institute of Science Tokyo, Department of Industrial Engineering and EconomicsIntelligent Voice Assistants (Alexa, Siri, etc.)Multilingual & Cross-Cultural Voice InteractionAgent Personality & AnthropomorphismCHI
Who did it? How User Agency is influenced by Visual Properties of Generated ImagesThe increasing proliferation of AI and GenAI requires new interfaces tailored to how their specific affordances and human requirements meet. As GenAI is capable of taking over tasks from users on an unprecedented scale, designing the experience of agency -- if and how users experience control over the process and responsibility over the outcome -- is crucial. As an initial step towards design guidelines for shaping agency, we present a study that explores how features of AI-generated images influence users' experience of agency. We use two measures; temporal binding to implicitly estimate pre-reflective agency and magnitude estimation to assess user judgments of agency. We observe that abstract images lead to more temporal binding than images with semantic meaning. In contrast, the closer an image aligns with what a user might expect, the higher the agency judgment. When comparing the experiment results with objective metrics of image differences, we find that temporal binding results correlate with semantic differences, while agency judgments are better explained by local differences between images. This work contributes towards a future where agency is considered an important design dimension for GenAI interfaces.2024JDJohanna K. Didion et al.Generative AI (Text, Image, Music, Video)Explainable AI (XAI)UIST
Comparing Perceptions of Static and Adaptive Proactive Speech AgentsA growing literature on speech interruptions describes how people interrupt one another with speech, but these behaviours have not yet been implemented in the design of artificial agents which interrupt. Perceptions of a prototype proactive speech agent which adapts its speech to both urgency and to the difficulty of the ongoing task it interrupts are compared against perceptions of a static proactive agent which does not. The study hypothesises that adaptive proactive speech modeled on human speech interruptions will lead to partner models which consider the proactive agent as a stronger conversational partner than a static agent, and that interruptions initiated by an adaptive agent will be judged as better timed and more appropriately asked. These hypotheses are all rejected however, as quantitative analysis reveals that participants view the adaptive agent as a poorer dialogue partner than the static agent and as less appropriate in the style it interrupts. Qualitative analysis sheds light on the source of this surprising finding, as participants see the adaptive agent as less socially appropriate and as less consistent in its interactions than the static agent.2024JEJustin Edwards et al.Conversational ChatbotsAgent Personality & AnthropomorphismCUI
Cross-Cultural Validation of Partner Models for Voice User Interfaces Recent research has begun to assess people's perceptions of voice user interfaces (VUIs) as dialogue partners, termed partner models. Current self-report measures are only available in English, limiting research to English-speaking users. To improve the diversity of user samples and contexts that inform partner modelling research, we translated, localized, and evaluated the Partner Modelling Questionnaire (PMQ) for non-English speaking Western (German, n=185) and East Asian (Japanese, n=198) cohorts where VUI use is popular. Through confirmatory factor analysis (CFA), we find that the scale produces equivalent levels of “goodness-to-fit” for both our German and Japanese translations, confirming its cross-cultural validity. Still, the structure of the communicative flexibility factor did not replicate directly across Western and East Asian cohorts. We discuss how our translations can open up critical research on cultural similarities and differences in partner model use and design, whilst highlighting the challenges for ensuring accurate translation across cultural contexts.2024KSKatie Seaborn et al.Voice User Interface (VUI) DesignMultilingual & Cross-Cultural Voice InteractionCUI
Using Speech Agents for Mood Logging within Blended Mental Healthcare: Mental Healthcare Practitioners' PerspectivesMood logging, where people track mood-related data, is commonly used to support mental healthcare. Speech agents could prove beneficial in supporting mood logging for clients. Yet we know little about how Mental Healthcare Practitioners (MHPs) view speech as a tool to support current care practices. Through a thematic analysis of semi-structured interviews with 15 MHPs, we show that MHPs see opportunities in the convenience, and the data richness that speech agents could afford. However, MHPs also saw this richness as noisy, with using speech potentially diminishing a client's focus on mood logging as an activity. MHPs were wary of overusing AI-based tools, expressing concerns around data ownership, access and privacy. We discuss the role of speech agents within blended care, outlining key considerations when using speech for mood logging in a blended mental healthcare context.2024OCOrla Cooney et al.Intelligent Voice Assistants (Alexa, Siri, etc.)Mental Health Apps & Online Support CommunitiesCUI
Disembodied, Asocial, and Unreal: How Users (Re)Interpret Designed Affordances of Social VRAlthough Social Virtual Reality (SVR) affordances are designed to enable embodied social activities and interactions within virtual environments, the ways that users perceive and interpret these affordances can shape how SVR platforms are used and experienced. In this study, we examined the design and use of SVR affordances based on qualitative survey data from 100 SVR users. We observed that user practices diverge in important ways from intended designs, adding complexity to conventional interpretations of SVR platforms as embodied social environments. This research highlights dynamic user behaviour in which users interpret and reconfigure the affordances of SVR platforms, ranging from asocial use cases to actions that reflect the current limits of embodied communication. We contribute findings that may improve SVR design by revealing opportunities to foreground user needs and expectations, leveraging both the designed possibilities of SVR and the interpretations of those possibilities.2024EKEugene Kukshinov et al.Social & Collaborative VRImmersion & Presence ResearchDIS
Silver-Tongued and Sundry: Exploring Intersectional Pronouns with ChatGPTChatGPT is a conversational agent built on a large language model. Trained on a significant portion of human output, ChatGPT can mimic people to a degree. As such, we need to consider what social identities ChatGPT simulates (or can be designed to simulate). In this study, we explored the case of identity simulation through Japanese first-person pronouns, which are tightly connected to social identities in intersectional ways, i.e., intersectional pronouns. We conducted a controlled online experiment where people from two regions in Japan (Kanto and Kinki) witnessed interactions with ChatGPT using ten sets of first-person pronouns. We discovered that pronouns alone can evoke perceptions of social identities in ChatGPT at the intersections of gender, age, region, and formality, with caveats. This work highlights the importance of pronoun use for social identity simulation, provides a language-based methodology for culturally-sensitive persona development, and advances the potential of intersectional identities in intelligent agents.2024TFTakao Fujii et al.Tokyo Institute of TechnologyMultilingual & Cross-Cultural Voice InteractionAgent Personality & AnthropomorphismHuman-LLM CollaborationCHI
Listening to the Voices: Describing Ethical Caveats of Conversational User Interfaces According to Experts and Frequent UsersAdvances in natural language processing and understanding have led to a rapid growth in the popularity of conversational user interfaces (CUIs). While CUIs introduce novel benefits, they also yield risks that may exploit people's trust. Although research looking at unethical design deployed through graphical user interfaces (GUIs) established a thorough taxonomy of so-called dark patterns, there is a need for an equally in-depth understanding in the context of CUIs. Addressing this gap, we interviewed 27 participants from three cohorts: researchers, practitioners, and frequent users of CUIs. Applying thematic analysis, we develop five themes reflecting each cohort's insights about ethical design challenges and introduce the CUI Expectation Cycle, bridging system capabilities and user expectations while respecting each theme's ethical caveats. This research aims to inform future work to consider ethical constraints while adopting a human-centred approach.2024TMThomas Mildner et al.University of BremenVoice User Interface (VUI) DesignAI Ethics, Fairness & AccountabilityDark Patterns RecognitionCHI
Supportive Fintech for Individuals with Bipolar Disorder: Financial Data Sharing Preferences for Longitudinal Care ManagementFinancial stability is a key challenge for individuals living with bipolar disorder (BD). Symptomatic periods in BD are associated with poor financial decision-making, contributing to a negative cycle of worsening symptoms and an increased risk of bankruptcy. There has been an increased focus on designing supportive financial technologies (fintech) to address varying and intermittent needs across different stages of BD. However, little is known about this population’s expectations and privacy preferences related to financial data sharing for longitudinal care management. To address this knowledge gap, we have deployed a factorial vignette survey using the Contextual Integrity framework. Our data from individuals with BD (N=480) shows that they are open to sharing financial data for long term care management. We have also identified significant differences in sharing preferences across age, gender, and diagnostic subtype. We discuss the implications of these findings in designing equitable fintech to support this marginalized community.2024JBJeff Brozena et al.Pennsylvania State UniversityCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Universal & Inclusive DesignCHI
Cooking With Agents: Designing Context-aware Voice InteractionVoice Agents (VAs) are touted as being able to help users in complex tasks such as cooking and interacting as a conversational partner to provide information and advice while the task is ongoing. Through conversation analysis of 7 cooking sessions with a commercial VA, we identify challenges caused by a lack of contextual awareness leading to irrelevant responses, misinterpretation of requests, and information overload. Informed by this, we evaluated 16 cooking sessions with a wizard-led context-aware VA. We observed more fluent interaction between humans and agents, including more complex requests, explicit grounding within utterances, and complex social responses. We discuss reasons for this, the potential for personalisation, and the division of labour in VA communication and proactivity. Then, we discuss the recent advances in generative models and the VAs interaction challenges. We propose limited context awareness in VAs as a step toward explainable, explorable conversational interfaces.2024RJRazan Jaber et al.Stockholm University , Stockholm UniversityVoice User Interface (VUI) DesignContext-Aware ComputingCHI
Benefits of Human-AI Interaction for Expert Users Interacting with Prediction Models: a Study on Marathon RunningUsers with large domain knowledge can be reluctant to use prediction models. This also applies to the sports domain, where running coaches rarely rely on marathon prediction tools for race-plan advice for their runners' next marathon. This paper studies the effect of adding interactivity to such prediction models, to incorporate and acknowledge users' domain knowledge. In think-aloud sessions and an online study, we tested an interactive machine learning tool that allowed coaches to indicate the importance of earlier races feeding into the model. Our results show that coaches deploy rich knowledge when working with the model on runners familiar to them, and their adaptations improved model accuracy. Those coaches who could interact with the model displayed more trust and acceptance in the resulting predictions.2024HMHeleen Muijlwijk et al.Human-LLM CollaborationAI-Assisted Decision-Making & AutomationIUI
Human Speakers Help Machine Listeners To account For Visual Asymmetries in DialogueHuman-machine dialogue (HMD) research debates the degree to which language production in this context is egocentric or allocentric. That is, the degree to which a person might take a machine’s perspective into account. Our study aims to identify whether users produce allocentric or egocentric language within speech-based HMD when there is asymmetry in the information available to both partners. Through an adapted referential communication task, we manipulated the presence or absence of visual distractors and occlusions, similarly to previous referential tasks used in psycholinguistic research. Results show that people are sensitive to the presence of distractors and occlusions and tend to produce more informative expressions to help machine partners account for the visual asymmetries. We discuss the fndings on how allocentric production in HMD is explained by how the division of labour manifests in spoken HMD. The fndings further our understanding of the language production mechanisms in HMD.2023PPPaola Raquel Peña et al.Voice User Interface (VUI) DesignHuman-LLM CollaborationCUI