This article presents an applied discussion of the possibility of integrating conversation analysis (CA) methodology into that of machine learning. The aim is to improve the detection of that which resembles disengagement in the interaction between a robot and a human. We offer a novel analytical assemblage at the heart of the two disciplines, and namely on the level of the annotation schemes provided by conversation analysis transcription methods. First, we demonstrate that the need for a stable structure in establishing (...) an interaction scenario and in designing robot behaviours does not prevent the emergence of ordinariness or creativity among the participants engaged in this interaction. Secondly, based on an actual case, we emphasize the possibility of systematicness in CA transcription to support the choice (a) of the categories targeted by prediction methods and defined by the annotation scheme, and (b) of the verbal and non-verbal features used to create prediction models. (shrink)

Research of tutoring in parent-infant interaction has shown that tutors – when presenting some action – modify both their verbal and manual performance for the learner. Investigating the sources and effects of the tutors’ action modifications, we suggest an interactional account of ‘motionese’. Using video-data from a semi-experimental study in which parents taught their 8- to 11-month old infants how to nest a set of differently sized cups, we found that the tutors’ action modifications functioned as an orienting device to (...) guide the infant’s visual attention. Action modification and the recipient’s gaze can be seen to have a reciprocal sequential relationship and to constitute a constant loop of mutual adjustments. Implications are discussed for developmental research and for robotic ‘Social Learning’. We argue that a robot system could use on-line feedback strategies to pro-actively shape a tutor’s action presentation as it emerges. (shrink)

The paper investigates the effects of a humanoid robot’s online feedback during a tutoring situation in which a human demonstrates how to make a frog jump across a table. Motivated by micro-analytic studies of adult-child-interaction, we investigated whether tutors react to a robot’s gaze strategies while they are presenting an action. And if so, how they would adapt to them. Analysis reveals that tutors adjust typical “motionese” parameters (pauses, speed, and height of motion). We argue that a robot – when (...) using adequate online feedback strategies – has at its disposal an important resource with which it could proactively shape the tutor’s presentation and help generate the input from which it would benefit most. These results advance our understanding of robotic “Social Learning” in that they suggest a paradigm shift towards considering human and robot as one interational learning system. Keywords: human-robot-interaction; feedback; adaptation; multimodality; gaze; conversation analysis; social learning; pro-active robot conduct. (shrink)

This contribution investigates the use of the Czech particle jako in naturally occurring conversations. Inspired by interactional research on unfinished or suspended utterances and on turn-final conjunctions and particles, the analysis aims to trace the possible development of jako from conjunction to a tag-like particle that can be exploited for mobilizing affiliative responses. Traditionally, jako has been described as conjunction used for comparing two elements or for providing a specification of a first element [“X like Y”]. In spoken Czech, however, (...) jako can be flexibly positioned within a speaking turn and does not seem to operate as a coordinating or hypotactic conjunction. As a result, prior studies have described jako as a polyfunctional particle. This article will try to shed light on the meaning of jako in spoken discourse by focusing on its apparent fuzzy or “filler” uses, i.e., when it is found in a mid-turn position in multi-unit turns and in the immediate vicinity of hesitations, pauses, and turn suspensions. Based on examples from mundane, video-recorded conversations and on a sequential and multimodal approach to social interaction, the analyses will first show that jako frequently frames discursive objects that co-participants should respond to. By using jako before a pause and concurrently adopting specific embodied displays, participants can more explicitly seek to mobilize responsive action. Moreover, as jako tends to cluster in multi-unit turns involving the formulation of subjective experience or stance, it can be shown to be specifically designed for mobilizing affiliative responses. Finally, it will be argued that the potential of jako to open up interactive turn spaces can be linked to the fundamental comparative semantics of the original conjunction. (shrink)

The transitions between turns at talk in conversation tend to occur quickly, with only a slight gap of approximately 100 to 300 ms between them. This estimate of central tendency, however, hides a wealth of complex variation, as a number of factors, such as the type of turns involved, have been shown to influence the timing of turn transitions. This article considers one specific type of turn that does not conform to the statistical trend, namely turns that deal with troubles (...) of speaking, hearing, and understanding, known as other-initiations of repair. The results of a quantitative analysis of 169 other-initiations of repair in face-to-face conversation reveal that the most frequent cases occur after gaps of approximately 700 ms. Furthermore, other-initiations of repair that locate a source of trouble in a prior turn specifically tend to occur after shorter gaps than those that do not, and those that correct errors in a prior turn, while rare, tend to occur without delay. An analysis of the transitions before other-initiations of repair, using methods of conversation analysis, suggests that speakers use the extra time (i) to search for a late recognition of the problematic turn, (ii) to provide an opportunity for the speaker of the problematic turn to resolve the trouble independently, (iii) and to produce visual signals, such as facial gestures. In light of these results, it is argued that other-initiations of repair take priority over other turns at talk in conversation and therefore are not subject to the same rules and constraints that motivate fast turn transitions in general. (shrink)