Robophobia is a recent and growing trend on social media, where users create humorous videos that play on the general fear of robots. While framed as jokes, these videos contribute to the public’s attitudes and expectations of robots, influencing what is socially and culturally acceptable. To investigate this emerging trend, we conducted a thematic analysis of 200 English-speaking TikTok videos using online ethnography to explore how users engage with robophobia and what implications this may have for the Human–Robot Interaction (HRI) field. Our findings show that robophobia on TikTok is predominantly expressed through humorous skits and verbal abuse of real-world robots in public spaces. Common themes include fears about humans in romantic relationships with robots, and frequent use of derogatory terms such as “clanker” to verbally "dehumanize" robots. The robophobia trend is culturally embedded and reveals people’s underlying attitudes and fears toward robots in society, both now and in the future. We discuss the implications of these findings for the field of Human–Robot Interaction (HRI), emphasizing how public expectations are shaped by cultural narratives, and stress the need for culturally sensitive, expectation-aware HRI research and robot design.

The use of social robots in many sectors of society is predicted to progressively increase. Therefore, exploring how expectations play a role in and change users’ experiences when interacting with these robots over time is necessary. From an interpretative and insight-driven approach, our aim was to explore how humans experience in-person interactions with the social robot Pepper, which was equipped with the OpenAI GPT-3 language model. Qualitative data from 62 video recordings of the interactions with Pepper and post-test interviews were collected from 31 participants. An experiential reflexive thematic analysis was applied. The main findings include various levels of interaction quality, different interaction strategies, and elements influencing the users’ expectations and experiences, which were synthesized into a coherent framework. It appears that the participants adapted their interaction strategies based on their expectations and the perceived capability of the robot, which influenced their experiences. This reveals that positive user experience is not solely determined by interaction quality, showing the interplay among these aspects when interacting with a social robot. To conclude, our findings underscore the intricate nature of the role of user expectations and experiences in social human–robot interaction. The work adds complementary qualitative approaches to the Human–Robot Interaction community to provide additional insights on interacting with social robots.

Learning-by-teaching, where a child learns through the act of teaching or helping a peer learn, has been shown to provide better learning outcomes than standard methods. While learning-by-teaching has been explored in some contexts in Human-Robot Interaction, we propose utilizing strategic robot errors to improve children's learning. We conducted an experimental study with thirty-one 6–8-year-old children in which a robot read a book to a child and the child was asked to point out and correct any mistakes the robot made. There were three conditions: no mistakes, simple mistakes, and targeted mistakes. While our data was insufficient to determine whether the type of errors the robot made affected children's learning, we did find the number of mistakes identified across conditions was different and discuss the effect they may have had on the sessions. We discuss implications of this research for pedagogical applications and future research ideas.

Highly anthropomorphic robots risk triggering expectation mismatch that can lead to disappointment when robot behavior falls short. This study investigates how actively teaching a social humanoid robot to narrate a story influences user expectations, negative attitudes, anxiety, and perceptions of storytelling quality, compared to passive observation. University students (N=40) were assigned to either a teaching or non-teaching condition. Teaching participants instructed the robot using speech and gestures, while the non-teaching group observed the robot narrate the resulting storytelling video. Results showed that active teaching reduced expectation shifts, suggesting greater alignment between user beliefs and robot capability. However, robot-related anxiety increased in the teaching group, while the non-teaching group consistently reported higher negative attitudes. Storytelling quality was more strongly influenced by robot anthropomorphism in the non-teaching group. Participants who blamed the robot gave lower storytelling ratings, whereas those who blamed the AI model or programmer were more lenient. These findings highlight the importance of managing expectations through interactive teaching of robot tutee.

Informed consent is an integral process in human-robot interaction (HRI); however, current practices have been criticized for overlooking the social, psychological, and embodied complexities of interacting with robots. Social robots’ embodied, human-like design and social behavior can lead to misaligned expectations that pose risks such as deception, overtrust, poor user experience, and psychological harm for users. Moreover, robots often collect personal data in ways that are not always visible or understood by users. Typically, informed consent does not address such issues, highlighting the need for consent processes tailored to HRI. In this paper, we reimagine informed consent and introduce the RoboConsent framework, drawing from previous HRI research highlighting these issues and feminist consent models that address power imbalances and move toward a user-centered process. The framework consists of five components that ensure meaningful informed consent and six principles that guide how it can be obtained. These work in tandem to create informed consent practices that address the unique dynamics of HRI.

The Negative Attitude toward Robots Scale (NARS) is one of the most common questionnaires used in the studies of human-robot interaction (HRI). It was established in 2004, and has since then been used in several domains to measure attitudes, both as main results and as a potential confounding factor. To better understand this important tool of HRI research, we reviewed the HRI literature with a specific focus on practice and reporting related to NARS. We found that the use of NARS is being increasingly reported, and that there is a large variation in how NARS is applied. The reporting is, however, often not done in sufficient detail, meaning that NARS results are often difficult to interpret, and comparing between studies or performing meta-analyses are even more difficult. After providing an overview of the current state of NARS in HRI, we conclude with reflections and recommendations on the practices and reporting of NARS.