Social robots as skilled ignorant peers for supporting learning.

When designing social robots for educational settings, there is often an emphasis on domain knowledge. This presents challenges: 1) Either robots must autonomously acquire domain knowledge, a currently unsolved problem in HRI, or 2) the designers provide this knowledge implying re-programming the robot for new contexts. Recent research explores alternative, relatively easier to port, knowledge areas like student rapport, engagement, and synchrony though these constructs are typically treated as the ultimate goals, when the final goal should be students' learning. Our aim is to propose a shift in how engagement is considered, aligning it naturally with learning. We introduce the notion of a skilled ignorant peer robot: a robot peer that has little to no domain knowledge but possesses knowledge of student behaviours conducive to learning, i.e., behaviours indicative of productive engagement as extracted from student behavioral profiles. We formally investigate how such a robot's interventions manipulate the children's engagement conducive to learning. Specifically, we evaluate two versions of the proposed robot, namely, Harry and Hermione, in a user study with 136 students where each version differs in terms of the intervention strategy. Harry focuses on which suggestions to intervene with from a pool of communication, exploration, and reflection inducing suggestions, while Hermione also carefully considers when and why to intervene. While the teams interacting with Harry have higher productive engagement correlated to learning, this engagement is not affected by the robot's intervention scheme. In contrast, Hermione's well-timed interventions, deemed more useful, correlate with productive engagement though engagement is not correlated to learning. These results highlight the potential of a social educational robot as a skilled ignorant peer and stress the importance of precisely timing the robot interventions in a learning environment to be able to manipulate moderating variable of interest such as productive engagement.

Is it possible for people to develop a sense of empathy toward humanoid robots and establish meaningful relationships with them?

Introduction: Empathy can be described as the ability to adopt another person's perspective and comprehend, feel, share, and respond to their emotional experiences. Empathy plays an important role in these relationships and is constructed in human-robot interaction (HRI). This systematic review focuses on studies investigating human empathy toward robots. We intend to define empathy as the cognitive capacity of humans to perceive robots as equipped with emotional and psychological states. Methods: We conducted a systematic search of peer-reviewed articles using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched Scopus, PubMed, Web of Science, and Embase databases. All articles were reviewed based on the titles, abstracts, and full texts by two investigators (EM and CS) who independently performed data collection. The researchers read the full-text articles deemed suitable for the study, and in cases of disagreement regarding the inclusion and exclusion criteria, the final decision was made by a third researcher (VLB). Results: The electronic search identified 484 articles. After reading the full texts of the selected publications and applying the predefined inclusion criteria, we selected 11 articles that met our inclusion criteria. Robots that could identify and respond appropriately to the emotional states of humans seemed to evoke empathy. In addition, empathy tended to grow more when the robots exhibited anthropomorphic traits. Discussion: Humanoid robots can be programmed to understand and react to human emotions and simulate empathetic responses; however, they are not endowed with the same innate capacity for empathy as humans.

Improving the Social Well-Being of Single Older Adults Using the LOVOT Social Robot: Qualitative Phenomenological Study.

BACKGROUND: This study examined the social well-being of single older adults through the companionship of a social robot, LOVOT (Love+Robot; Groove X). It is designed as a companion for older adults, providing love and affection through verbal and physical interaction. We investigated older adults' perceptions of the technology and how they benefitted from interacting with LOVOT, to guide the future development of social robots. OBJECTIVE: This study aimed to use a phenomenological research design to understand the participants' experiences of companionship provided by the social robot. Our research focused on (1) examining the social well-being of single older adults through the companionship of social robots and (2) understanding the perceptions of single older adults when interacting with social robots. Given the prevalence of technology use to support aging, understanding single older adults' social well-being and their perceptions of social robots is essential to guide future research on and design of social robots. METHODS: A total of 5 single women, aged 60 to 75 years, participated in the study. The participants interacted independently with the robot for a week in their own homes and then participated in a poststudy interview to share their experiences. RESULTS: In total, 4 main themes emerged from the participants' interactions with LOVOT, such as caring for a social robot, comforting presence of the social robot, meaningful connections with the social robot, and preference for LOVOT over pets. CONCLUSIONS: The results indicate that single older adults can obtain psychosocial support by interacting with LOVOT. LOVOT is easily accepted as a companion and makes single older adults feel like they have a greater sense of purpose and someone to connect with. This study suggests that social robots can provide companionship to older adults who live alone. Social robots can help alleviate loneliness by allowing single older adults to form social connections with robots as companions. These findings are particularly important given the rapid aging of the population and the increasing number of single-person households in Singapore.

Task-Motion Planning System for Socially Viable Service Robots Based on Object Manipulation.

This paper presents a software architecture to implement a task-motion planning system that can improve human-robot interactions by including social behavior when social robots provide services related to object manipulation to users. The proposed system incorporates four main modules: knowledge reasoning, perception, task planning, and motion planning for autonomous service. This system adds constraints to the robot motions based on the recognition of the object affordance from the perception module and environment states from the knowledge reasoning module. Thus, the system performs task planning by adjusting the goal of the task to be performed, and motion planning based on the functional aspects of the object, enabling the robot to execute actions consistent with social behavior to respond to the user's intent and the task environment. The system is verified through simulated experiments consisting of several object manipulation services such as handover and delivery. The results show that, by using the proposed system, the robot can provide different services depending on the situation, even if it performs the same tasks. In addition, the system demonstrates a modular structure that enables the expansion of the available services by defining additional actions and diverse planning modules.

Do Children with Autism Spectrum Disorders Show Selective Trust in Social Robots?

PURPOSE: Previous researches suggest that social robots can facilitate the learning of children with Autism Spectrum Disorder (ASD) by enhancing their interests, engagement, and attention. However, there is limited understanding regarding whether children with ASD can learn directly from the testimony of social robots and whether they can remain vigilant based on the perceived accuracy of these robots. Therefore, the present study was conducted to examine whether children with ASD demonstrated selective trust towards social robots. METHODS: Twenty-nine children with ASD between ages of 4-7 years, and 38 typically-developing (TD) age and IQ-matched peers participated in classic selective trust tasks. During the tasks, they learned the names of novel objects from either a pair of social robots or a pair of human informants, where one informant had previously been established as accurate and the other inaccurate. RESULTS: Children with ASD trusted information from an accurate social robot over an inaccurate one, similar to their performance with human informants. However, compared to TD children, children with ASD exhibited lower levels of selective trust regardless of the type of informants they learned from. CONCLUSIONS: Our study suggests that children with ASD can selectively trust and acquire knowledge from social robots, shedding light on the potential use of social robots in supporting individuals with ASD.

Social Robots for Meaningful Seated Activities: Acceptance & Use by Older Adults.

Healthy aging requires the maintenance of good physical and cognitive activity. However, as they age, older adults often experience a decline in physical and cognitive activity, leading to a more sedentary lifestyle. Some older adults may not have a choice but to become increasingly sedentary as they age due to injury or deteriorated physicality. As such, they require assistive technologies to aid in their daily lives and activities to maintain healthy cognitive function. Social Robots are a newer form of assistive technology, specifically designed for social interactions and gameplay. As with other assistive technologies, compliance barriers to their acceptance and use for meaningful, seated activities among older adults are expected. To better explore this phenomenon, improve quality of life and understand what drives older adults to accept and use newer forms of technology like social robots, this conceptual paper conjoins two theoretical frameworks: The Activity Theory of Aging (ATA) and the Unified Theory of Acceptance and Use of Technology (UTAUT). As social robots hold great promise for improving the quality of life for older adults, exploring what driving factors could enable their greater acceptance and use is essential to furthering this field of study within Australia.

Efficacy of relational agents for loneliness across age groups: a systematic review and meta-analysis.

BACKGROUND: Loneliness is a serious public health concern. Although previous interventions have had some success in mitigating loneliness, the field is in search of novel, more effective, and more scalable solutions. Here, we focus on "relational agents", a form of software agents that are increasingly powered by artificial intelligence and large language models (LLMs). We report on a systematic review and meta-analysis to investigate the impact of relational agents on loneliness across age groups. METHODS: In this systematic review and meta-analysis, we searched 11 databases including Ovid MEDLINE and Embase from inception to Sep 16, 2022. We included randomised controlled trials and non-randomised studies of interventions published in English across all age groups. These loneliness interventions, typically attempt to improve social skills, social support, social interaction, and maladaptive cognitions. Peer-reviewed journal articles, books, book chapters, Master's and PhD theses, or conference papers were eligible for inclusion. Two reviewers independently screened studies, extracted data, and assessed risk of bias via the RoB 2 and ROBINS-I tools. We calculated pooled estimates of Hedge's g in a random-effects meta-analysis and conducted sensitivity and sub-group analyses. We evaluated publication bias via funnel plots, Egger's test, and a trim-and-fill algorithm. FINDINGS: Our search identified 3,935 records of which 14 met eligibility criteria and were included in our meta-analysis. Included studies comprised 286 participants with individual study sample sizes ranging from 4 to 42 participants (x̄ = 20.43, s = 11.58, x̃ = 20). We used a Bonferroni correction with αBonferroni = 0.05 / 4 = 0.0125 and applied Knapp-Hartung adjustments. Relational agents reduced loneliness significantly at an adjusted αBonferroni (g = -0.552; 95% Knapp-Hartung CI, -0.877 to -0.226; P = 0.003), which corresponds to a moderate reduction in loneliness. CONCLUSION: Our results are currently the most comprehensive of their kind and provide promising evidence for the efficacy of relational agents. Relational agents are a promising technology that can alleviate loneliness in a scalable way and that can be a meaningful complement to other approaches. The advent of LLMs should boost their efficacy, and further research is needed to explore the optimal design and use of relational agents. Future research could also address shortcomings of current results, such as small sample sizes and high risk of bias. Particularly young audiences have been overlooked in past research.

How did COVID-19 pandemic affect the older adults' needs for robot technologies in Japan?: comparison of participatory design workshops during versus after the COVID-19 pandemic.

Social technology can improve the quality of social lives of older adults (OAs) and mitigate negative mental and physical health outcomes. When people engage with technology, they can do so to stimulate social interaction (stimulation hypothesis) or disengage from their real world (disengagement hypothesis), according to Nowland et al.'s model of the relationship between social Internet use and loneliness. External events, such as large periods of social isolation like during the COVID-19 pandemic, can also affect whether people use technology in line with the stimulation or disengagement hypothesis. We examined how the COVID-19 pandemic affected the social challenges OAs faced and their expectations for robot technology to solve their challenges. We conducted two participatory design (PD) workshops with OAs during and after the COVID-19 pandemic. During the pandemic, OAs' primary concern was distanced communication with family members, with a prevalent desire to assist them through technology. They also wanted to share experiences socially, as such OA's attitude toward technology could be explained mostly by the stimulation hypothesis. However, after COVID-19 the pandemic, their focus shifted towards their own wellbeing. Social isolation and loneliness were already significant issues for OAs, and these were exacerbated by the COVID-19 pandemic. Therefore, such OAs' attitudes toward technology after the pandemic could be explained mostly by the disengagement hypothesis. This clearly reflect the OA's current situation that they have been getting further digitally excluded due to rapid technological development during the pandemic. Both during and after the pandemic, OAs found it important to have technologies that were easy to use, which would reduce their digital exclusion. After the pandemic, we found this especially in relation to newly developed technologies meant to help people keep at a distance. To effectively integrate these technologies and avoid excluding large parts of the population, society must address the social challenges faced by OAs.

Would you be impressed: applying principles of magic to chatbot conversations.

A magician's trick and a chatbot conversation have something in common: most of their audiences do not know how they work. Both are also constrained by their own limitations: magicians by the constraints of biology and physics, and dialogue systems by the status of current technology. Magicians and chatbot creators also share a goal: they want to engage their audience. But magicians, unlike the designers of dialogue systems, have centuries of practice in gracefully skirting limitations in order to engage their audience and enhance a sense of awe. In this paper, we look at these practices and identify several key principles of magic and psychology to apply to conversations between chatbots and humans. We formulate a model of communication centered on controlling the user's attention, expectations, decisions, and memory based on examples from the history of magic. We apply these magic principles to real-world conversations between humans and a social robot and evaluate their effectiveness in a Magical conversation setting compared to a Control conversation that does not incorporate magic principles. We find that human evaluators preferred interactions that incorporated magical principles over interactions that did not. In particular, magical interactions increased 1) the personalization of experience, 2) user engagement, and 3) character likability. Firstly, the magical experience was "personalized." According to survey results, the magical conversation demonstrated a statistically significant increase in "emotional connection" and "robot familiarity." Therefore, the personalization of the experience leads to higher levels of perceived impressiveness and emotional connection. Secondly, in the Magical conversation, we find that the human interlocutor is perceived to have statistically-significantly higher engagement levels in four of seven characteristics. Thirdly, participants judged the robot in the magical conversation to have a significantly greater degree of "energeticness,""humorousness," and "interestingness." Finally, evaluation of the conversations with questions intended to measure contribution of the magical principals showed statistically-significant differences for five out of nine principles, indicating a positive contribution of the magical principles to the perceived conversation experience. Overall, our evaluation demonstrates that the psychological principles underlying a magician's showmanship can be applied to the design of conversational systems to achieve more personalized, engaging, and fun interactions.

Promising directions for human-robot interactions defined by older adults.

Introduction: Older adults are engaging more and more with voice-based agent and social robot technologies, and roboticists are increasingly designing interactions for these systems with older adults in mind. Older adults are often not included in these design processes, yet there are many opportunities for older adults to collaborate with design teams to design future robot interactions and help guide directions for robot development. Methods: Through a year-long co-design project, we collaborated with 28 older adults to understand the key focus areas that older adults see promise in for older adult-robot interaction in their everyday lives and how they would like these interactions to be designed. This paper describes and explores the robot-interaction guidelines and future directions identified by older adults, specifically investigating the change and trajectory of these guidelines through the course of the co-design process from the initial interview to the design guideline generation session to the final interview. Results were analyzed through an adapted ethnographic decision tree modeling approach to understand older adults' decision making surrounding the various focus areas and guidelines for social robots. Results: Overall, over the course of the co-design process between the beginning and end, older adults developed a better understanding of the robot that translated to them being more certain of their attitudes of how they would like a robot to engage with them in their lives. Older adults were more accepting of transactional functions such as reminders and scheduling and less open to functions that would involve sharing sensitive information and tracking and/or monitoring of them, expressing concerns around surveillance. There was some promise in robot interactions for connecting with others, body signal monitoring, and emotional wellness, though older adults brought up concerns around autonomy, privacy, and naturalness of the interaction with a robot that need to be further explored. Discussion: This work provides guidance for future interaction development for robots that are being designed to interact with older adults and highlights areas that need to be further investigated with older adults to understand how best to design for user concerns.

When a notification at the right time is not enough: the reminding process for socially assistive robots in institutional care.

Reminding is often identified as a central function of socially assistive robots in the healthcare sector. The robotic reminders are supposed to help people with memory impairments to remember to take their medicine, to drink and eat, or to attend appointments. Such standalone reminding technologies can, however, be too demanding for people with memory injuries. In a co-creation process, we developed an individual reminder robot together with a person with traumatic brain injury and her care personnel. During this process, we learned that while current research describe reminding as a prototypical task for socially assistive robots, there is no clear definition of what constitutes a reminder nor that it is based on complex sequences of interactions that evolve over time and space, across different actions, actors and technologies. Based on our data from the co-creation process and the first deployment, we argue for a shift towards a sequential and socially distributed character of reminding. Understanding socially assistive robots as rehabilitative tools for people with memory impairment, they need to be reconsidered as interconnected elements in institutional care practices instead of isolated events for the remindee.

No playing around with robots? Ambivalent attitudes toward the use of Paro in elder care.

This paper explores the ways in which health care professionals, family carers, and older persons expressed attitudes and opinions on using Paro, a social robot designed to stimulate patients with dementia. Thereafter, we critically evaluate existing prejudicial views toward Paro users to provide recommendations for its future use. Using an exploratory qualitative interview method, we recruited a total of 67 participants in Switzerland. They included 23 care professionals, 17 family carers, and 27 older persons. Data obtained were analyzed thematically. Study findings present general agreement that Paro is an appealing and beneficial social robot, but it is not a tool that everyone feels comfortable with. Because it is perceived as "child play," it would be demeaning for competent adults to play with such things. Consequently, Paro is appropriate only for persons with dementia. These findings brought forth ethical concerns about deception, infantilization, and respecting older persons' dignity. The idea of who is an appropriate Paro user led to our discussions on predicting future Paro users. The meaning of using social robotics in nursing homes can be conditioned by a rigid interpretation of adulthood and playful behavior. To protect future selves when one is living with dementia from prejudices, it may be useful for older persons and their loved ones to plan their future care situations to ensure that they are treated in accordance with their delineated decisions.

Social robotics as an adjuvant during the hospitalization process in pediatric oncology patients.

OBJECTIVE: To describe the experience of implementing social robotics as an adjuvant during the hospitalization process in pediatric oncology patients. METHODS: Before and after cohort study, applying an intervention with the Lego Mindstorms EV3 kit in patients between 8 and 17 years old that are hospitalized with a cancer diagnosis. We excluded patients from the intensive care unit or when their treating physician recommended so. The intervention consisted of a three-phase workshop: an open architecture story, building a car robot using the Lego Mindstorm EV3 kit, and cooperative playing activities such as races and passing obstacles. RESULTS: Thirteen patients received the intervention with robotic lego. The median age was 15 years (IQR = 3), and 84.6% of the population (n = 11) were male. We found significant improvement in the language (topic management p = .011 and communicative intention p = .034). Other characteristics improved, but not significantly (self-care activities index, catching). No adverse events occurred during the intervention. CONCLUSIONS: The results of this pilot study suggest that implementing social robotics during hospitalization in children with cancer is a therapeutic adjuvant and safe intervention that promotes better communication, self-care, and a physical activity improvement. For future studies, the impact of this intervention could be measured in hospitalized pediatric cancer patients.

Children's anthropomorphism of inanimate agents.

This review article examines the extant literature on animism and anthropomorphism in infants and young children. A substantial body of work indicates that both infants and young children have a broad concept of what constitutes a sentient agent and react to inanimate objects as they do to people in the same context. The literature has also revealed a developmental pattern in which anthropomorphism decreases with age, but social robots appear to be an exception to this pattern. Additionally, the review shows that children attribute psychological properties to social robots less so than people but still anthropomorphize them. Importantly, some research suggests that anthropomorphism of social robots is dependent upon their morphology and human-like behaviors. The extent to which children anthropomorphize robots is dependent on their exposure to them and the presence of human-like features. Based on the existing literature, we conclude that in infancy, a large range of inanimate objects (e.g., boxes, geometric figures) that display animate motion patterns trigger the same behaviors observed in child-adult interactions, suggesting some implicit form of anthropomorphism. The review concludes that additional research is needed to understand what infants and children judge as social agents and how the perception of inanimate agents changes over the lifespan. As exposure to robots and virtual assistants increases, future research must focus on better understanding the full impact that regular interactions with such partners will have on children's anthropomorphizing. This article is categorized under: Psychology > Learning Cognitive Biology > Cognitive Development Computer Science and Robotics > Robotics.

Assisted Robots in Therapies for Children with Autism in Early Childhood.

Children with autism spectrum disorder (ASD) have deficits that affect their social relationships, communication, and flexibility in reasoning. There are different types of treatment (pharmacological, educational, psychological, and rehabilitative). Currently, one way to address this problem is by using robotic systems to address the abilities that are altered in these children. The aim of this review will be to analyse the effectiveness of the incorporation of the different robotic systems currently existing in the treatment of children up to 10 years of age diagnosed with autism. A systematic review has been carried out in the PubMed, Scopus, Web of Science, and Dialnet databases, with the following descriptors: child, autism, and robot. The search yielded 578 papers, and nine were selected after the application of the PRISMA guideline. The quality of the studies was analysed with the PEDRo scale, and only those with a score between four and six were selected. From this study, the conclusion is that the use of robots, in general, improves children's behaviour in the short term, but longer-term experiences are necessary to achieve more conclusive results.

Qualitative study on domestic social robot adoption and associated security concerns among older adults in Slovenia.

Introduction: Despite the increasing use of domestic social robots by older adults, there remains a significant knowledge gap regarding attitudes, concerns, and potential adoption behavior in this population. This study aims to categorize older adults into distinct technology adoption groups based on their attitudes toward domestic social robots and their behavior in using the existing technology. Methods: An exploratory qualitative research design was used, involving semi-structured interviews with 24 retired Slovenian older adults aged 65 years or older, conducted between 26 June and 14 September 2023. Results: Four distinct groups of older adults were identified: (1) Cautious Optimists, (2) Skeptical Traditionalists, (3) Positive Optimists, and (4) Technophiles based on eight characteristics. Discussion: These groups can be aligned with the categories of the Diffusion of Innovation Theory. Privacy and security concerns, influenced by varying levels of familiarity with the technology, pose barriers to adoption. Perceived utility and ease of use vary considerably between groups, highlighting the importance of taking into account the different older adults. The role of social influence in the adoption process is complex, with some groups being more receptive to external opinions, while others exhibit more autonomous decision-making.

Development and Validation of the Attitudes towards Social Robots Scale.

The idea of artificially created social robots has a long tradition. Today, attitudes towards robots play a central role in the field of healthcare. Our research aimed to develop a scale to measure attitudes towards robots. The survey consisted of nine questions on attitudes towards robots, sociodemographic questions, the SWOP-K9, measuring self-efficacy, optimism, and pessimism, and the BFI-10, measuring personality dimensions. Structural relations between the items were detected using principal components analysis (PCA) with Varimax rotation. Correlations and Analysis of Variance were used for external validation. In total, 214 participants (56.1% female, mean age: 30.8 ± 14.4 years) completed the survey. The PCA found two main components, "Robot as a helper and assistant" (RoHeA) and "Robot as an equal partner" (RoEqP), with four items each explaining 53.2% and 17.5% of the variance with a Cronbach's α of 0.915 and 0.768. In the personality traits, "Conscientiousness" correlated weakly with both subscales and "Extraversion" correlated with RoHeA, while none the subscales of the SWOP-K9 significantly correlated with RoEqP or RoHeA. Male participants scored significantly higher than female participants. Our survey yielded a stable and convergent two-factor instrument that exhibited convincing validity and complements other findings in the field. The ASRS can easily be used to describe attitudes towards social robots in human society. Further research, however, should be carried out to investigate the discriminant and convergent validity of the ASRS.

Attachment to robots and therapeutic efficiency in mental health.

Previous studies in the mental health context have demonstrated that interactions with social robots can improve the mood and cognitive capacities of their users, and enhance their quality of life. In this Perspective article, our goal is to systematize the possible roles of social robots and to point out that different roles require different levels of attachment. We argue that the attachment between the client and the (robot) therapist is a fundamental ingredient of any helping relationship and that the full potential of using social robots in mental health settings can only be realized if the strength of attachment is appropriately correlated with the type of relationship established.

Cardiology professionals' views of social robots in augmenting heart failure patient care.

Aims: Social robots are arriving to the modern healthcare system. Whether patients with heart failure, a prevalent chronic disease with high health and human costs would derive benefit from a social robot intervention has not been investigated empirically. Diverse healthcare provider's perspectives are needed to develop an acceptable and feasible social robot intervention to be adopted for the clinical benefit of patients with heart failure. Using a qualitative research design, this study investigated healthcare providers' perspectives of social robot use in heart failure patient care. Methods and results: Interdisciplinary healthcare providers from a tertiary care cardiac hospital completed a structured individual interview and a supplemental questionnaire. The framework method was used to analyse the qualitative data. Respondents (n = 22; saturation was reached with this sample; 77% female; 52% physicians) were open to using social robots to augment their practice, particularly with collecting pertinent data and providing patient and family education and self-management prompts, but with limited responsibility for direct patient care. Prior to implementation, providers required robust evidence of: value-added beyond current remote patient monitoring devices, patient and healthcare provider partnerships, streamlined integration into existing practice, and capability of supporting precision medicine goals. Respondents were concerned that social robots did not address and masked broader systemic issues of healthcare access and equity. Conclusion: The adoption of social robots is a viable option to assist in the care of patients with heart failure, albeit in a restricted capacity. The results inform the development of a social robotic intervention for patients with heart failure, including improving social robot efficiencies and increasing their uptake, while protecting patients' and providers' best interest.

Real-time emotion generation in human-robot dialogue using large language models.

Affective behaviors enable social robots to not only establish better connections with humans but also serve as a tool for the robots to express their internal states. It has been well established that emotions are important to signal understanding in Human-Robot Interaction (HRI). This work aims to harness the power of Large Language Models (LLM) and proposes an approach to control the affective behavior of robots. By interpreting emotion appraisal as an Emotion Recognition in Conversation (ERC) tasks, we used GPT-3.5 to predict the emotion of a robot's turn in real-time, using the dialogue history of the ongoing conversation. The robot signaled the predicted emotion using facial expressions. The model was evaluated in a within-subjects user study (N = 47) where the model-driven emotion generation was compared against conditions where the robot did not display any emotions and where it displayed incongruent emotions. The participants interacted with the robot by playing a card sorting game that was specifically designed to evoke emotions. The results indicated that the emotions were reliably generated by the LLM and the participants were able to perceive the robot's emotions. It was found that the robot expressing congruent model-driven facial emotion expressions were perceived to be significantly more human-like, emotionally appropriate, and elicit a more positive impression. Participants also scored significantly better in the card sorting game when the robot displayed congruent facial expressions. From a technical perspective, the study shows that LLMs can be used to control the affective behavior of robots reliably in real-time. Additionally, our results could be used in devising novel human-robot interactions, making robots more effective in roles where emotional interaction is important, such as therapy, companionship, or customer service.