Self-disclosure and the social sharing of emotions facilitate social relationships and can positively affect people's well-being. Nevertheless, individuals might refrain from engaging in these interpersonal communication behaviours with other people, due to socio-emotional barriers, such as shame and stigma. Social robots, free from these human-centric judgements, could encourage openness and overcome these barriers. Accordingly, this paper reviews the role of self-disclosure and social sharing of emotion in human-robot interactions (HRIs), particularly its implications for emotional well-being and the dynamics of social relationship building between humans and robots. We investigate the transition of self-disclosure dynamics from traditional human-to-human interactions to HRI, revealing the potential of social robots to bridge socio-emotional barriers and provide unique forms of emotional support. This review not only highlights the therapeutic potential of social robots but also raises critical ethical considerations and potential drawbacks of these interactions, emphasising the importance of a balanced approach to integrating robots into emotional support roles. The review underscores a complex but promising frontier at the intersection of technology and emotional well-being, advocating for careful consideration of ethical standards and the intrinsic human need for connection as we advance in the development and application of social robots.

Large language models (LLMs) are increasingly used for verbal interaction in social robots, yet prompt design in human-robot interaction (HRI) remains underspecified. As a result, robots may present hallucinated capabilities, unclear behavioural boundaries, and misleading personas. This paper develops a framework for prompt design in LLM-based robots and introduces a structured prompt template comprising eight functional components through which robot behaviour can be specified, bounded, and adapted. The framework is grounded in a review of prior LLM-based HRI work and complemented by survey and discussion data from HRI experts gathered at the Robo-Identity workshop at IEEE RO-MAN 2025 (N=27). The qualitative findings highlight limited legibility of robot personality, the need for user adaptation, and strong ethical concerns about safety, deception, and governance. Based on these findings, we present prompting guidelines accompanied by proof-of-concept template as a structured design and reporting aid for HRI research. We argue that prompt design should be treated as a socio-technical problem rather than a minor implementation detail, requiring explicit capability boundaries, transparent behavioural assumptions, and context-sensitive safeguards to support reliable and interpretable HRI.

Emotion regulation is a crucial skill for managing emotions in everyday life, yet finding a constructive and accessible method to support these processes remains challenging due to their cognitive demands. In this study, we explore how regular interactions with a social robot, conducted in a structured yet familiar environment within university halls and departments, can provide effective support for emotion regulation through cognitive reappraisal. Twenty-one students participated in a five-session study at a university hall or department, where the robot, powered by a large language model (GPT-3.5), facilitated structured conversations, encouraging the students to reinterpret emotionally charged situations they shared with the robot. Quantitative and qualitative results indicate significant improvements in emotion self-regulation, with participants reporting better understanding and control of their emotions. The intervention led to significant changes in constructive emotion regulation tendencies and positive effects on mood and sentiment after each session. The findings also demonstrate that repeated interactions with the robot encouraged greater emotional expressiveness, including longer speech disclosures, increased use of affective language, and heightened facial arousal. Notably, expressiveness followed structured patterns aligned with the reappraisal process, with expression peaking during key reappraisal moments, particularly when participants were prompted to reinterpret negative experiences. The qualitative feedback further highlighted how the robot fostered introspection and provided a supportive space for discussing emotions, enabling participants to confront long-avoided emotional challenges. These findings demonstrate the potential of robots to effectively assist in emotion regulation in familiar environments, offering both emotional support and cognitive guidance.

Recent research in affective robots has recognized their potential in supporting human well-being. Due to rapidly developing affective and artificial intelligence technologies, this field of research has undergone explosive expansion and advancement in recent years. In order to develop a deeper understanding of recent advancements, we present a systematic review of the past 10 years of research in affective robotics for wellbeing. In this review, we identify the domains of well-being that have been studied, the methods used to investigate affective robots for well-being, and how these have evolved over time. We also examine the evolution of the multifaceted research topic from three lenses: technical, design, and ethical. Finally, we discuss future opportunities for research based on the gaps we have identified in our review - proposing pathways to take affective robotics from the past and present to the future. The results of our review are of interest to human-robot interaction and affective computing researchers, as well as clinicians and well-being professionals who may wish to examine and incorporate affective robotics in their practices.

Institutional and social barriers in higher education often prevent students with disabilities from effectively accessing support, including lengthy procedures, insufficient information, and high social-emotional demands. This study empirically explores how disabled students perceive robot-based support, comparing two interaction roles, one information based (signposting) and one disclosure based (sounding board), and two embodiment types (physical robot/disembodied voice agent). Participants assessed these systems across five dimensions: perceived understanding, social energy demands, information access/clarity, task difficulty, and data privacy concerns. The main findings of the study reveal that the physical robot was perceived as more understanding than the voiceonly agent, with embodiment significantly shaping perceptions of sociability, animacy, and privacy. We also analyse differences between disability types. These results provide critical insights into the potential of social robots to mitigate accessibility barriers in higher education, while highlighting ethical, social and technical challenges. CCS Concepts center dot Human-centered computing -> Accessibility design and evaluation methods; center dot Computer systems organization -> Robotics; center dot Social and professional topics -> People with disabilities.

Emotion expression is central to human–robot interaction, yet little is known about how people interpret affect on robots with sparse, non-anthropomorphic expressive capabilities. This study examined how people perceive emotional expressions displayed by Reachy Mini (Pollen Robotics and Hugging Face), a low-degree-of-freedom (low-DoF) robot with a constrained and distinctly non-human expressive repertoire. In an online within-subjects study, 100 participants viewed 10 short video clips of Reachy Mini expressing different emotions and, for each clip, identified the perceived emotion, rated its valence and arousal, and evaluated the robot on social-perception traits. Exact emotion recognition was modest overall and varied considerably across expressions, with anger, sadness, and interest recognized more reliably than emotions such as love, pleasure, shame, and disgust. However, participants were generally more successful at recovering broader affective meaning than exact emotion labels, particularly along valence and arousal dimensions. Emotional expressions also shaped social evaluation, as positive expressions were perceived as warmer and more sociable than negative ones, and animacy varied less across conditions. These findings suggest that even constrained robotic expressions can communicate affective meaning and influence social impressions, positioning Reachy Mini as a useful benchmark for studying affective communication in low-DoF robots.

This workshop examines the design and evaluation of behavioral paradigms that effectively elicit and measure proactive behavior in Intelligent Virtual Agents (IVA). Current paradigms focus mainly on agent behavior. However, it remains unclear how these paradigms effectively help to elicit and measure proactive agent interactions and produce ecologically valid data, particularly for paradigms that promote the use of different modalities during interaction beyond text or speech. We invite researchers to discuss methodologies for developing tasks that not only structure agent behaviors but also provide meaningful insights into the social and cognitive processes involved in proactive interactions.

As social robots and other artificial agents become more conversationally capable, it is important to understand whether the content and meaning of self-disclosure towards these agents changes depending on the agent's embodiment. In this study, we analysed conversational data from three controlled experiments in which participants self-disclosed to a human, a humanoid social robot, and a disembodied conversational agent. Using sentence embeddings and clustering, we identified themes in participants' disclosures, which were then labelled and explained by a large language model. We subsequently assessed whether these themes and the underlying semantic structure of the disclosures varied by agent embodiment. Our findings reveal strong consistency: thematic distributions did not significantly differ across embodiments, and semantic similarity analyses showed that disclosures were expressed in highly comparable ways. These results suggest that while embodiment may influence human behaviour in human-robot and human-agent interactions, people tend to maintain a consistent thematic focus and semantic structure in their disclosures, whether speaking to humans or artificial interlocutors.

People often engage in self-disclosure and social sharing when trying to cope with emotional distress. This study introduces a novel long-term intervention designed to help informal caregivers cope with emotional distress by self-disclosing towards a social robot. Research indicates that informal caregivers frequently face challenges in handling the emotional and practical demands of caregiving, often experiencing a lack of social support and limited social interaction. Accordingly, we explored the extent of informal caregivers’ self-disclosure behaviour towards a social robot (Pepper, SoftBank Robotics) over time, and how their perceptions of the robot evolved. Additionally, we examined how this intervention affected caregivers’ moods, perceptions of the robot as comforting, feelings of loneliness, stress levels, as well as its impact on their emotion regulation. We replicated a previous long-term experiment [1] with a dedicated sample of informal caregivers who interacted with Pepper 10 times over five weeks, discussing everyday topics. Our results show that caregivers increasingly self-disclosed to the robot over time, perceiving it as more social and competent. Participants’ moods improved following interactions, and they viewed the robot as increasingly comforting. They also reported feeling progressively less lonely and stressed. Thus, our findings with informal caregivers replicated those of [1]. Moreover, after the intervention, caregivers reported greater acceptance of their caregiving roles, reappraising it more positively, and reduced feelings of blame towards others. These results highlight the potential of social robots to provide emotional support for individuals coping with emotional distress.

Social robots are increasingly being explored as tools to support emotional wellbeing, particularly in non-clinical settings. Drawing on a range of empirical studies and practical deployments, this paper outlines six key insights that highlight both the opportunities and challenges in using robots to promote mental wellbeing. These include (1) the lack of a single, objective measure of wellbeing, (2) the fact that robots don't need to act as companions to be effective, (3) the growing potential of virtual interactions, (4) the importance of involving clinicians in the design process, (5) the difference between one-off and long-term interactions, and (6) the idea that adaptation and personalization are not always necessary for positive outcomes. Rather than positioning robots as replacements for human therapists, we argue that they are best understood as supportive tools that must be designed with care, grounded in evidence, and shaped by ethical and psychological considerations. Our aim is to inform future research and guide responsible, effective use of robots in mental health and wellbeing contexts.

Chatbots are emerging as a self-management tool for supporting mental health, appearing across commercial and healthcare settings. Whilst chatbots are valued for their perceived lack of judgement, they lack the emotional intelligence and empathy to build trust and rapport with users. A resulting debate questions whether chatbots facilitate or hinder self-disclosure. This study presents a within-subjects experimental design investigating the parameters of self-disclosure in social interactions with chatbots in an open domain. Participants engaged in two short social interactions with two chatbots: one with the knowledge they were conversing with a chatbot and one with the false belief they were conversing with a human. A significant difference was found across both treatments, with participants disclosing more to the chatbot that was introduced as a human, as well as perceiving themselves to do so, perceiving this chatbot as more comforting, and to be demonstrating higher rates of agency and experience compared to the chatbot that was introduced as a chatbot. However, significant findings also indicated participants' disclosures to the chatbot that was introduced as a chatbot were more sentimental, and they found it to be friendlier compared to the chatbot that was introduced as a human. These results indicate that whilst cues to a chatbot’s human origins enhance self-disclosure and perceptions of mind, when the artificial agent is perceived against one’s social expectations, it may be viewed negatively on social factors that require higher cognitive processing.

As social robots and other artificial agents become more conversationally capable, it is important to understand whether the content and meaning of self-disclosure towards these agents changes depending on the agent's embodiment. In this study, we analysed conversational data from three controlled experiments in which participants self-disclosed to a human, a humanoid social robot, and a disembodied conversational agent. Using sentence embeddings and clustering, we identified themes in participants' disclosures, which were then labelled and explained by a large language model. We subsequently assessed whether these themes and the underlying semantic structure of the disclosures varied by agent embodiment. Our findings reveal strong consistency: thematic distributions did not significantly differ across embodiments, and semantic similarity analyses showed that disclosures were expressed in highly comparable ways. These results suggest that while embodiment may influence human behaviour in human-robot and human-agent interactions, people tend to maintain a consistent thematic focus and semantic structure in their disclosures, whether speaking to humans or artificial interlocutors.

Large Language Models primarily operate through text-based inputs and outputs, yet human emotion is communicated through both verbal and non-verbal cues, including facial expressions. While Vision-Language Models analyze facial expressions from images, they are resource-intensive and may depend more on linguistic priors than visual understanding. To address this, this study investigates whether LLMs can infer affective meaning from dimensions of facial expressions-Valence and Arousal values, structured numerical representations, rather than using raw visual input. VA values were extracted using Facechannel from images of facial expressions and provided to LLMs in two tasks: (1) categorizing facial expressions into basic (on the IIMI dataset) and complex emotions (on the Emotic dataset) and (2) generating semantic descriptions of facial expressions (on the Emotic dataset). Results from the categorization task indicate that LLMs struggle to classify VA values into discrete emotion categories, particularly for emotions beyond basic polarities (e.g., happiness, sadness). However, in the semantic description task, LLMs produced textual descriptions that align closely with human-generated interpretations, demonstrating a stronger capacity for free text affective inference of facial expressions.

As conversational agents increasingly engage in emotionally supportive dialogue, it is important to understand how closely their interactions resemble those in traditional therapy settings. This study investigates whether the concerns shared with a robot align with those shared in human-to-human (H2H) therapy sessions, and whether robot responses semantically mirror those of human therapists. We analyzed two datasets: one of interactions between users and professional therapists (Hugging Face's NLP Mental Health Conversations), and another involving supportive conversations with a social robot (QTrobot from LuxAI) powered by a large language model (LLM, GPT-3.5). Using sentence embeddings and K-means clustering, we assessed cross-agent thematic alignment by applying a distance-based cluster-fitting method that evaluates whether responses from one agent type map to clusters derived from the other, and validated it using Euclidean distances. Results showed that 90.88

Conversational User Interfaces (CUIs), including chatbots, virtual agents and social robots, are increasingly shaping how we communicate, seek support and access services. Yet, as these systems grow more sophisticated, concerns about bias and fairness in their design and deployment have become increasingly urgent. We propose a multidimensional approach to bias and fairness in CUIs that spans four interconnected themes: conceptual grounding, verbal communication, multimodal expression and interactional dynamics. Rather than framing bias merely as a technical flaw, we argue that it should be understood as a relational, interactional and design-based phenomenon. Accordingly, in this workshop, we aim to foster critical discussion around how CUIs encode social norms, perpetuate or mitigate exclusion, and shape perceptions of fairness through their language, embodiment and behaviour. By bringing together researchers, designers and policymakers, the workshop will explore pathways towards more equitable and transparent CUIs. The goal is to promote a relational understanding of fairness, one that centres user experience and social context, to guide future work in conversational AI.

Subjective self-disclosure is an important feature of human social interaction. While much has been done in the social and behavioural literature to characterise the features and consequences of subjective self-disclosure, little work has been done thus far to develop computational systems that are able to accurately model it. Even less work has been done that attempts to model specifically how human interactants self-disclose with robotic partners. It is becoming more pressing as we require social robots to work in conjunction with and establish relationships with humans in various social settings. In this paper, our aim is to develop a custom multimodal attention network based on models from the emotion recognition literature, training this model on a large self-collected self-disclosure video corpus, and constructing a new loss function, the scale preserving cross entropy loss, that improves upon both classification and regression versions of this problem. Our results show that the best performing model, trained with our novel loss function, achieves an F1 score of 0.83, an improvement of 0.48 from the best baseline model. This result makes significant headway in the aim of allowing social robots to pick up on an interaction partner's self-disclosures, an ability that will be essential in social robots with social cognition.

Loneliness and stress are prevalent among young adults and are linked to significant psychological and health-related consequences. Social robots may offer a promising avenue for emotional support, especially when considering the ongoing advancements in conversational AI. This study investigates how repeated interactions with a social robot influence feelings of loneliness and perceived stress, and how such feelings are reflected in the themes of user disclosures towards the robot. Participants engaged in a five-session robot-led intervention, where a large language model powered QTrobot facilitated structured conversations designed to support cognitive reappraisal. Results from linear mixed-effects models show significant reductions in both loneliness and perceived stress over time. Additionally, semantic clustering of 560 user disclosures towards the robot revealed six distinct conversational themes. Results from a Kruskal-Wallis H-test demonstrate that participants reporting higher loneliness and stress more frequently engaged in socially focused disclosures, such as friendship and connection, whereas lower distress was associated with introspective and goal-oriented themes (e.g., academic ambitions). By exploring both how the intervention affects well-being, as well as how well-being shapes the content of robot-directed conversations, we aim to capture the dynamic nature of emotional support in huma-robot interaction.

Large Language Models (LLMs) primarily operate through textbased inputs and outputs, yet emotion is communicated through both verbal and non-verbal cues, including facial expressions. While Vision-Language Models analyse facial expressions from images, they are resource-intensive and may depend more on linguistic priors than visual understanding. To address this, this study investigates whether LLMs can infer affective meaning from dimensions of facial expressions-Valence-Arousal (VA) values, structured numerical representations. VA values were extracted using Facechannel from images of facial expressions (from IIMI and EMOTIC datasets) and provided to three LLMs in two tasks: (1) classifying facial expressions into basic and complex emotions and (2) generating semantic descriptions of facial expressions. The results indicate that LLMs struggle to classify VA values into discrete emotion categories, particularly for emotions beyond basic polarities. However, LLMs produced semantic descriptions that align closely with humangenerated interpretations, demonstrating a stronger capacity for free-text affective inference of facial expressions.