Second Language Tutoring Using Social Robots: A Large-Scale Study

Vogt, Paul; Berghe, Rianne van den; Haas, Mirjam de; Hoffman, Laura; Kanero, Junko; Mamus, Ezgi; Montanier, Jean-Marc; Oranç, Cansu; Oudgenoeg‐Paz, Ora; García, Daniel Hernández; Papadopoulos, Fotios; Schodde, Thorsten; Verhagen, Josje; Wallbridgell, Christopher D.; Willemsen, Bram; Wit, Jan de; Belpaeme, Tony; Göksun, Tilbe; Kopp, Stefan; Krahmer, Emiel; Küntay, Ayli̇n C.; Leseman, Paul; Pandey, Amit Kumar

doi:10.1109/hri.2019.8673077

Cited by 103 publications

(104 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversational systems lack understanding of meaning and context and typically act on scripts in a pre-designed type of conversation (Serholt, 2018). Although there are noteworthy examples of somewhat long-term studies of autonomous social robots being conducted in classrooms (Serholt and Barendregt, 2016;Alves-Oliveira et al, 2019;Davison et al, 2020), many studies still require some degree of teleoperation for the interaction to work smoothly, particularly when it comes to verbal communication (Kory-Westlund and Breazeal, 2019;Vogt et al, 2019). This suggests that interaction trouble will likely continue to be a prominent feature of conversational interactions with autonomous social robots.…”

Section: Discussionmentioning

confidence: 99%

Trouble and Repair in Child–Robot Interaction: A Study of Complex Interactions With a Robot Tutee in a Primary School Classroom

et al. 2020

View full text Add to dashboard Cite

Today, robots are studied and expected to be used in a range of social roles within classrooms. Yet, due to a number of limitations in social robots, robot interactions should be expected to occasionally suffer from troublesome situations and breakdowns. In this paper, we explore this issue by studying how children handle interaction trouble with a robot tutee in a classroom setting. The findings have implications not only for the design of robots, but also for evaluating their benefit in, and for, educational contexts. In this study, we conducted video analysis of children's group interactions with a robot tutee in a classroom setting, in order to explore the nature of these troubles in the wild. Within each group, children took turns acting as the primary interaction partner for the robot within the context of a mathematics game. Specifically, we examined what types of situations constitute trouble in these child-robot interactions, the strategies that individual children employ to cope with this trouble, as well as the strategies employed by other actors witnessing the trouble. By means of Interaction Analysis, we studied the video recordings of nine group interaction sessions (n = 33 children) in primary school grades 2 and 4. We found that sources of trouble related to the robot's social norm violations, which could be either active or passive. In terms of strategies, the children either persisted in their attempts at interacting with the robot by adapting their behavior in different ways, distanced themselves from the robot, or sought the help of present adults (i.e., a researcher in a teacher role, or an experimenter) or their peers (i.e., the child's classmates in each group). In terms of the witnessing actors, they addressed the trouble by providing guidance directed at the child interacting with the robot, or by intervening in the interaction. These findings reveal the unspoken rules by which children orient toward social robots, the complexities of child-robot interaction in the wild, and provide insights on children's perspectives and expectations of social robots in classroom contexts.

show abstract

Section: Discussionmentioning

confidence: 99%

Trouble and Repair in Child–Robot Interaction: A Study of Complex Interactions With a Robot Tutee in a Primary School Classroom

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In these cases, we recommend preregistering the hypotheses and analysis plans before conducting the actual evaluation. 3 Preregistration is still uncommon in NLG and other fields of AI (with a few notable exceptions, like for instance Vogt et al, 2019), but it addresses an important issue with human evaluations. Conducting and analysing a human experiment is like entering a garden of forking paths (Gelman and Loken, 2013): along the way researchers have many choices to make, and even though each choice may be small and seemingly innocuous, collectively they can have a substantial effect on the outcome of the statistical analyses, to the extent that it becomes possible to present virtually every finding as statistically significant (Simmons et al, 2011;Wicherts et al, 2016).…”

Section: Statisticsmentioning

confidence: 99%

Best practices for the human evaluation of automatically generated text

Lee

Gatt

Miltenburg

et al. 2019

Proceedings of the 12th International Conference on Natural Language Generation

Self Cite

119

View full text Add to dashboard Cite

Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated, with a particularly high degree of variation in the way that human evaluation is carried out. This paper provides an overview of how human evaluation is currently conducted, and presents a set of best practices, grounded in the literature. With this paper, we hope to contribute to the quality and consistency of human evaluations in NLG.

show abstract

“…As a note, there are other studies where the mode of presentation did not have the expected impact. For instance, Vogt et al [51] reported from a study where social robots were used to tutor children in second language learning. They could not find the expected differences in the learning effect between modes that were different in their implementation (tablet only vs. use of a social robot, the latter with and without the use of gestures), although they performed a large-scale study.…”

Section: Discussion Of the Resultsmentioning

confidence: 99%

Strengthening Engagement in Science Understanding with Learning Trails

Leister

Tjostheim

Joryd

et al. 2019

MTI

View full text Add to dashboard Cite

The Norwegian Museum of Science and Technology has developed a learning concept for school classes in science centres named “learning trails”. In this concept, groups of students perform a series of thematically related experiments with installations in the science centre. The learning trails are designed to support the generic learning outcomes for science centre visits. We argue that the previously developed Engagement Profile can be used to translate exhibit properties into both media forms and generic learning outcomes for such learning concepts. Further, we implemented the learning trails in two modes: one mode used paper-based content to guide the students, while the other mode supported the use of tablet PCs where engaging content is triggered when the students approach the location of an experiment in the learning trail. We studied the engagement factors of the learning trails and observed how school classes use these. In a study with 113 students from lower secondary school (age 16), they answered short questionnaires that were integrated into the implementation of the learning trails. While the concept of the learning trails was evaluated positively, we could not find significant differences in how engaging the two implemented modes were.

show abstract

Second Language Tutoring Using Social Robots: A Large-Scale Study

Cited by 103 publications

References 35 publications

Trouble and Repair in Child–Robot Interaction: A Study of Complex Interactions With a Robot Tutee in a Primary School Classroom

Trouble and Repair in Child–Robot Interaction: A Study of Complex Interactions With a Robot Tutee in a Primary School Classroom

Best practices for the human evaluation of automatically generated text

Strengthening Engagement in Science Understanding with Learning Trails

Contact Info

Product

Resources

About