Skip to content

Computational formalisation of CSCL theories using Bayesian models

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 associational), q2 · 1 of 1 report an effect size · 1 claim rests on one study

Description

The authors recommend striving for a unified language, such as a formalisation strategy, in which different CSCL theories can be expressed, proposing the Bayesian framework as a formal language within reach for CSCL researchers. Formal modelling "makes us think deeply about our theories", highlights gaps and lack of clarity, contributes to open theorising by making assumptions explicit, and yields compact, easily exchanged theories.

Accounts

  • Formalise theories with computational models (e.g., Bayesian framework) to counter epistemic fragmentation in CSCL: The authors recommend striving for a unified language, such as a formalisation strategy, in which different CSCL theories can be expressed, proposing the Bayesian framework as a formal language within reach for CSCL researchers. Formal modelling "makes us think deeply about our theories", highlights gaps and lack of clarity, contributes to open theorising by making assumptions explicit, and yields compact, easily exchanged theories. (Baker et al. (2024))
  • Ground the design of automated collaborative-process analysis models in theoretical constructs from social and cognitive psychology: The article recommends that computational models for automated collaborative-learning process analysis be structured using theories from social and cognitive psychology, so that models capture deep structure in the data and generalize better. The authors state that "The significance of this finding from a methodological standpoint is that it highlights the importance of considering the theoretical foundation for a construct when setting up a machine learning model to use for automated assessment." Theory informed both the feature representation and the DBN model structure, enabling an unsupervised approach requiring neither hand-labeled data nor hand-crafted features. (Gweon et al. (2013))

Claims

Key Sources

  • Baker, M., Reimann, P. (2024). CSCL: a learning and collaboration science?. International Journal of Computer-Supported Collaborative Learning. https://doi.org/10.1007/s11412-024-09433-4
  • Gweon, G., Jain, M., McDonough, J., Raj, B., & Rosé, C. P. (2013). Measuring prevalence of other-oriented transactive contributions using an automated measure of speech style accommodation. Computer-Supported Collaborative Learning (2013). doi:10.1007/s11412-013-9172-5
Page metadata
Field Value
type research-method
id computational-formalisation-of-cscl-theories-using-bayesian-models
title Computational formalisation of CSCL theories using Bayesian models
description The authors recommend striving for a unified language, such as a formalisation strategy, in which different CSCL theories can be expressed, proposing the Bayesian framework as a formal language within reach for CSCL researchers.
status review
generated by process:settle-candidates on 2026-10-18
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.