Interrogating Methods for Analyzing Social Construction of Knowledge Online

• In Event: Studying How Learning Design Decisions Contribute to the Learner Experience in Online Environments

Abstract

The Interaction Analysis Model (IAM) (Gunawardena et al., 1997) is one of the most frequently employed frameworks to guide the qualitative analysis of social construction of knowledge (SCK) online. However, qualitative analysis is time consuming, and precludes immediate feedback to revise online courses while being delivered. To expedite analysis with a large data set, this study explores how a Neural Network (NN) algorithm can automatically predict phases of knowledge construction using IAM. The methods interrogated the extent to which the NN predicted phases of IAM approximated a human coder’s qualitative analysis. Results yielded a 34% accuracy rate. Future studies should consider training the NN with larger datasets to improve accuracy to provide real time feedback to students and designers.

Authors

• Charlotte N. Gunawardena, University of New Mexico
  Presenting Author

• Yan Chen, University of Nevada - Las Vegas
  Presenting Author

• Nick V. Flor, University of New Mexico
  Presenting Author

• Damien Sanchez, The University of New Mexico
  Presenting Author