Measuring prevalence of other-oriented transactive contributions using an automated measure of speech style accommodation

Abstract

This paper contributes to a theory-grounded methodological foundation for automatic collaborative learning process analysis. It does this by illustrating how insights from the social psychology and sociolinguistics of speech style provide a theoretical framework to inform the design of a computational model. The purpose of that model is to detect prevalence of an important group knowledge integration process in raw speech data. Specifically, this paper focuses on assessment of transactivity in dyadic discussions, where a transactive contribution is operationalized as one where reasoning is made explicit, and where that reasoning builds on a prior reasoning statement within the discussion. Transactive contributions can be either self-oriented, where the contribution builds on the speaker's own prior contribution, or other-oriented, where the contribution builds on a prior contribution of a conversational partner. Other-oriented transacts are particularly central to group knowledge integration processes. An unsupervised Dynamic Bayesian Network model motivated by concepts from Speech Accommodation Theory is presented and then evaluated on the task of estimating prevalence of other-oriented transacts in dyadic discussions. The evaluation demonstrates a significant positive correlation between an automatic measure of speech style accommodation and prevalence of other-oriented transacts (R = .36, p< .05).

Towards Careful Practices for Automated Linguistic Analysis of Group Learning

“…Research on speech style accommodation has found that conversants may shift their speaking style within an interaction, becoming either more similar or less similar to one another. By examining speech style accommodation as a social cue, we can better determine if conversational participants are working to build common ground with one another, which should also be reflected in the prevalence of transactive statements building on others' ideas (Gweon et al, 2013). Indeed, our work has shown that our automatic measures of speech style accommodation are significantly positively correlated with otheroriented transactive statements.…”

“…In our prior work, we developed and applied machine learning techniques for automatic analysis of transactivity in discussion forums (Rosé et al, 2008), chat transcripts (Joshi & Rosé, 2007), transcribed group discussions (Ai, Sionti, Wang, & Rosé, 2010), and speech recordings of dyadic discussions (Gweon et al, 2013). When we attempt to build computational models of this and other dimensions, we learn from inspecting the models we build from our data, and those insights contribute back to our understanding of the constructs themselves.…”

“…Here we use as our example an effort to model speech style accommodation using unsupervised Dynamic Bayesian Networks as one step towards automating analysis of transactivity in speech Gweon et al, 2013). Research on speech style accommodation has found that conversants may shift their speaking style within an interaction, becoming either more similar or less similar to one another.…”

Collaboration scripts and scaffolding

“…Both studies presented so far build on recent work in the area of automated collaborative process analysis (Rosé et al 2008;Mu et al 2012;Gweon et al 2013) and dynamic support for collaborative learning (Wang et al 2011;Adamson et al 2014), which have been of interest in this journal for some time (e.g., Berland et al 2015;Dascalu et al 2015;Erkens and Janssen 2008). This line for research gives news perspectives on what computational tools can do to support learning.…”

A decade of CSCL

“…Meanwhile-with the use of CSCL technologies like social media, discussion environments and MOOCs-the need for using computer processing of discourse has grown tremendously in order to bring pivotal interchanges to the attention of teachers and others (Law & Laferrière 2013). IjCSCL has periodically reported on such efforts (Erkens & Janssen 2008;Gweon et al 2013;Mu et al 2012;Rose et al 2008).…”