Four-participant group conversation: A facilitation robot controlling engagement density as the fourth participant

Abstract

In this paper, we present a framework for facilitation robots that regulate imbalanced engagement density in a four-participant conversation as the forth participant with proper procedures for obtaining initiatives. Four is the special number in multiparty conversations. In three-participant conversations, the minimum unit for multiparty conversations, social imbalance, in which a participant is left behind in the current conversation, sometimes occurs. In such scenarios, a conversational robot has the potential to objectively observe and control situations as the fourth participant. Consequently, we present model procedures for obtaining conversational initiatives in incremental steps to harmonize such four-participant conversations. During the procedures, a facilitator must be aware of both the presence of dominant participants leading the current conversation and the status of any participant that is left behind. We model and optimize these situations and procedures as a partially observable Markov decision process (POMDP), which is suitable for real-world sequential decision processes. The results of experiments conducted to evaluate the proposed procedures show evidence of their acceptability and feeling of groupness.

Assistive Robots for the Social Management of Health: A Framework for Robot Design and Human–Robot Interaction Research

“…A more detailed investigation into the specifics of how a robot should act to make sure people can participate meaningfully and equally in conversation is described by Matsuyama et al [21]. They used a robot for facilitating a conversation between three participants in which two participants had a strong engagement with each other evidenced by lots of back-and-forth conversation turns, and one of the participants was left out (side-participant).…”

“…Most of the studies in social HRI focus on the role of the robot as interactant rather than as assistant to humanhuman social interactions. However, the field has begun to pay more attention to robots being part of and even intervening in social interactions between humans in roles such as group member [20,21], facilitator [22,23], or moderator [24,25]. HRI studies of robots intervening in human-human interactions vary widely in their scope, and are scattered across domains of application, using very different robot designs in a variety of context.…”

Automatic detection of children's engagement using non-verbal features and ordinal learning

“…collaboration and engagement) [1,2], in particular, between children [3,4]. In small group play setting, it was observed that children exhibit different levels and types of involvement, i.e.…”

Automatic analysis of children’s engagement using interactional network features

“…For example, a robot could play the role of a side-participant and support interactions of a participant who is not engaged with others, called "weak engagement" in triadic interactions [2]. In child-child interactions, this weak engagement problem could often be observed since children (6-9 yrs) are still developing social skills at their own pace.…”

“…In child-child interactions, this weak engagement problem could often be observed since children (6-9 yrs) are still developing social skills at their own pace. Moreover, children learn social interactions in collaborative play in which "harmonised and unharmonised engagement" [2] can often occur. "harmonised engagement" is defined as the situation where children interact substantially and keep their connections during play.…”