A new study by CRI Research Fellows Liubov Tupikina and Marc Santolini, and their collaborator Sasha Poquet (University of South Australia and National University of Singapore), has been accepted for publication and is available at here! This work has been accepted in the Proceedings of the 10th International Conference on Learning Analytics and Knowledge (LAK ’20), March 23-27, 2020, Frankfurt, Germany(https://lak20.solaresearch.org/) LAK is a highly selective conference at the heart of the learning analytics community, aiming to derive behavioral and performance metrics of individual learners from digital data.
Learning analytics (LA) strives to improve learner experiences by leveraging digital learner traces. Capturing learner interactions in the form of network representations makes it possible to visualize and analyze social dynamics in online course forums, making it a popular element of learning analytics dashboards.
In this article, the authors explore how online forum networks used by students during classes can be used as tools to build social networks from which we can derive information about collaborative learning. In this construction, the inferred social networks carry the properties of the forum network, so that a high degree may simply reflect high posting activity. The paper presents a methodology for dissociating forum activity from social connectivity using several generative models. The authors develop a methodological framework for robustly inferring such social networks from online forum data, while taking into account the natural diversity of classroom configurations. This work is relevant for scientists interested in social interactions and learner networks in digital learning, and more generally for researchers wishing to derive informative social network models from online forums.
The graphs included here represent the visualization of social networks obtained from online classroom forum data in Australia.
