Abstract. Engagement is the single best predictor of successful learning for children with intellectual disabilities yet achieving engagement with pupils who have profound or multiple disabilities (PMD) presents a challenge to educators. Robots have been used to engage children with autism but are they effective with pupils whose disabilities limit their ability to control other technology? Learning objectives were identified for eleven pupils with PMD and a humanoid robot was programmed to enable teachers to use it to help pupils achieve these objectives. These changes were evaluated with a series of eleven case studies where teacherpupil dyads were observed during four planned video recorded sessions. Engagement was rated in a classroom setting and during the last session with the robot. Video recordings were analysed for duration of engagement and teacher assistance and number of goals achieved. Rated engagement was significantly higher with the robot than in the classroom. Observations of engagement, assistance and goal achievement remained at the same level throughout the sessions suggesting no reduction in the novelty factor.

Artificial intelligence tools for education (AIEd) have been used to automate the provision of learning support to mainstream learners. One of the most innovative approaches in this field is the use of data and machine learning for the detection of a student’s affective state, to move them out of negative states that inhibit learning, into positive states such as engagement. In spite of their obvious potential to provide the personalisation that would give extra support for learners with intellectual disabilities, little work on AIEd systems that utilise affect recognition currently addresses this group. Our system used multimodal sensor data and machine learning to first identify three affective states linked to learning (engagement, frustration, boredom) and second determine the presentation of learning content so that the learner is maintained in an optimal affective state and rate of learning is maximised. To evaluate this adaptive learning system, 67 participants aged between 6 and 18 years acting as their own control took part in a series of sessions using the system. Sessions alternated between using the system with both affect detection and learning achievement to drive the selection of learning content (intervention) and using learning achievement alone (control) to drive the selection of learning content. Lack of boredom was the state with the strongest link to achievement, with both frustration and engagement positively related to achievement. There was significantly more engagement and less boredom in intervention than control sessions, but no significant difference in achievement. These results suggest that engagement does increase when activities are tailored to the personal needs and emotional state of the learner and that the system was promoting affective states that in turn promote learning. However, longer exposure is necessary to determine the effect on learning.

Virtual human technologies are now being widely explored as therapy tools for mental health disorders including depression and anxiety. These technologies leverage the ability of the virtual agents to engage in naturalistic social interactions with a user to elicit behavioural expressions which are indicative of depression and anxiety. Research efforts have focused on optimising the human-like expressive capabilities of the virtual human, but less attention has been given to investigating the effect of virtual human mediation on the expressivity of the user. In addition, it is still not clear what an optimal task is or what task characteristics are likely to sustain long term user engagement. To this end, this paper describes the design and evaluation of virtual human-mediated tasks in a user study of 56 participants. Half the participants complete tasks guided by a virtual human, while the other half are guided by text on screen. Self-reported PHQ9 scores, biosignals and participants' ratings of tasks are collected. Findings show that virtual-human mediation influences behavioural expressiveness and this observation differs for different depression severity levels. It further shows that virtual human mediation improves users' disposition towards tasks. CCS CONCEPTS• Human-centered computing → User studies; • Applied computing → Health informatics; • Computing methodologies → Artificial intelligence.

Voice assistants in future autonomous vehicles may play a major role in supporting the driver during periods of a transfer of control with the vehicle (handover and handback). However, little is known about the effects of different qualities of the voice assistant on its perceived acceptability, and thus its potential to support the driver's trust in the vehicle. A desktop study was carried out with 18 participants, investigating the effects of three gendered voices and different wording of prompts during handover and handback driving scenarios on measures of acceptability. Participants rated prompts by the voice assistant in nine different driving scenarios, using 5-point Likert style items in a during and post-study questionnaire as well as a short interview at the end. A commanding/formally worded prompt was rated higher on most of the desirable measures of acceptability as compared to an informally worded prompt. The 'Matthew' voice used was perceived to be less artificial and more desirable than the 'Joanna' voice and the gender-ambiguous 'Jordan' voice; however, we caution against interpreting these results as indicative of a general preference of gender, and instead discuss our results to throw light on the complex socio-phonetic nature of voices (including gender) and wording of voice assistants, and the need for careful consideration while designing the same. Results gained facilitate the drawing of insights needed to take better care when designing the voice and wording for voice assistants in future autonomous vehicles. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

No abstract