Year: 2024
Type: conference-paper
Abstract: The ability to assess conversational interactions creates a challenge in assessing speaker turns over time, including frequency of occurrence, duration of each turn, and connecting speakers in a multi-speaker context. This is of particular interest in the analysis of teacher-student or adult-child interactions in learning spaces. The creation of a visualization mechanism capable of providing a high-level representation of the overall conversational interactions without overburdening educators in reviewing student/child learning engagement would be valuable. In this study, we explore the creation of chord diagrams as a way to analyze talk time between a child and adult speakers in learning spaces. The proposed illustration is suggested to provide an opportunity to study the variations in speech duration and the interaction among speakers that are involved in the communication with each other over a certain time learning duration. The data set in this study contains a spontaneous conversational speech which was recorded with aid of the LENA device. Here we analyze conversations having engagement for one session as transcribed by the UT Dallas-CRSS transcription team. Figure 1 illustrates the proposed Chord Diagram which consists of the following three speaker categories: PC, SC, and AD/TE. Red is used to represent the adult speaker (or teacher, AD/TE), blue is used to represent the secondary child speaker (SC), and lastly green is shown to represent the primary child speaker (PC). Each arc island along the circumference represents a specific conversational exchange. The width of the arc island represents the total duration of the talk time between the related speakers. For example, in the figure it shows that the thickest arc is the highlighted one having a total duration of 49.1 seconds of engagement between the speakers. The length of the circumference of the Diagram represents the total talk time duration for considered speaker (e.g., 525 sec for PC).
DOI: 10.18260/1-2--39222
Institutions: The University of Texas at Dallas, University of Kansas
Language: English
Subfield: Education
Field: Social Sciences
Domain: Social Sciences
SDG: Quality education
Open Access status: bronze
OpenAlex ID: W4391352278
