Technology-supported learning is an integral part of everyday learning. Adaptive tutoring systems are already widespread, but they often lack the social component of learning. Social robots can provide personalized tutoring as well as social interaction and can thus address this challenge. In this contribution, we present a model to personalize the behavior of a social robot tutor for higher education which has both a theoretical as well as an empirical foundation: Theoretically, it is based on the well-known Self-Determination Theory (SDT) that assumes that intrinsic motivation is strongly related to the fulfillment of three basic human needs, namely the need for autonomy, competence, and relatedness. Empirically it is based on the results of four studies with university students that demonstrate that particularly adaptation on a social level is beneficial. The final model considers the personalization of the robotic tutor’s behavior based on the current learning content and its social behavior and also considers a long-term perspective for multi-session learning. Thereby each of the three layers of SDT is addressed in multiple ways. This is one of the first models that contain a long-term perspective and is particularly designed for higher education.

Advancing digitization in working environments brings up the necessity of lifelong learning as well as technology-supported employee training. Research on social robots has already demonstrated their potential to support adults in their learning process. In this study, we focus on potential benefits of applying a social robot for employee training. We conducted a field study in cooperation with a company and set-up two conditions: a robot-supported learning environment and the onscreen learning environment the company usually uses for employee training. Our results show a positive perception of the robot and participants of the robot condition reported significantly more enjoyment while learning. Half of the participants are willing to use it again in the future: some prefer the robot-supported training over the onscreen training, while others were interested to use both options. However, the other half stick with onscreen learning in the future and there were no significant differences between motivation and learning success between the two groups.

Learning in universities challenges students to engage in self-directed learning, which requires a high degree of self-motivation while individual support by teachers is limited. Research on social robots has already demonstrated their potential to support students in their learning process. In this paper, we focus on the benefits of adaptivity of a robotic tutor in a higher education scenario. To this end, we conducted a field study over three sessions over the course of a semester and implemented two conditions (adaptive and non-adaptive) of a robotic tutor to support students with exam preparation. After participant learned with both version in random order in the first two sessions, their preferred condition was used in the third session. Our results show that significantly more students preferred to learn with the adaptive robotic tutor. Additionally, participation resulted in significantly better exam performance compared to the average of the course. However, there was no significant difference in the learning experience such as motivation or need satisfaction between conditions.

Social robots found their way into several economic fields of our daily life, e.g., as info points in shopping malls or hotels. However, research on robots in the tourism sector is still in its infancy. Conducting three online studies, we examined the design of robotic speech for a robotic concierge. Providing self-disclosure via speech or using local dialect did not affect robot acceptance and attitudes. In contrast, informal speech led to higher likeability and perceived warmth of the robot concierge. Overall, our results reveal positive evaluations of our robotic concierge regardless of its manipulation.

Abstract Reading is an essential ability and a cornerstone of education. However, learning to read can be challenging for children. To scaffold young learners, a number of reading interventions were developed, including a syllable-based approach in German, which has proven to be successful, but resource and time consuming through individual interaction by educators. To improve the reach of the reading intervention, we present the first step towards a digital intervention, following an iterative design approach. In this contribution, we present the implementation of a digital prototype, developed with the feedback of expert evaluations, as well as an interview study with second graders. The results of interviews with children showed that the app is suitable to be applied in the target age group, that children had fun using it and were motivated to further do so. In a next step towards a meaningful digitalization of the analogue intervention, we extended the application based on the evaluation results and conducted a usability evaluation of the extended app. The study as well as the usability evaluation provides design implications for iteratively transferring the analogue concept into a digital application.

The benefits of social robots in educational contexts were mainly investigated with children, but also bear great potential to support learners and teachers in higher education. To further explore the potential of social robots in the context of university teaching, we implemented a robot-supported learning environment as a complementary training to a university course. To learn more about the students' perspective and attitudes towards the integration of robots in their education, we conducted a field study with qualitative interviews as data collection method. Our results show a clear positive perception of the robot-supported learning environment, and indicate a positive impact on the learning outcomes. Most students suppose an additional value in the presence of the robot compared to traditional on-screen scenario or self-study, and perceived the robot to increase their motivation, attention and concentration. We found a clear interest of the students to use the learning environment again in the future. However, more individualized feedback was desired.