Dialogism Meets Language Models for Evaluating Involvement in CSCL Conversations

The use of technology as a facilitator in learning environments has become increasingly prevalent with the global pandemic caused by COVID-19. As such, computer-supported collaborative learning (CSCL) gains a wider adoption in contrast to traditional learning methods. At the same time, the need for automated tools capable of assessing and stimulating collaboration between participants has become more stringent, as human monitoring of the increasing volume of conversations becomes overwhelming. This paper introduces a method grounded in dialogism for evaluating students’ involvement in chat conversations based on semantic chains computed using language models. These semantic chains reflect emergent voices from dialogism that span and interact throughout the conversation. Our integrated method uses contextual information captured by BERT transformer models to identify links in a chain that connects semantically related concepts from a voice uttered by one or more participants. Two types of visualizations were generated to depict the longitudinal propagation and the transversal inter-animation of voices within the conversation. In addition, a list of handcrafted features derived from the constructed chains and computed for each participant is introduced. Several machine learning algorithms were tested using these features to evaluate the extent to which semantic chains are predictive of student involvement in chat conversations. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

READERBENCH - AUTOMATED FEEDBACK GENERATION FOR ESSAYS IN ROMANIAN

The development of online environments has transformed written communication into one of the most frequently used types of interactions between individuals;this effect has increased even more during the COVID-19 pandemic, which imposed physical distancing restrictions. As writing is a key skill in everyday activities, it is important for people to have strong skills and to be capable to communicate their thoughts and beliefs in a structured form. This paper introduces automated scoring and feedback mechanisms for Romanian, derived from an online collection of freely available essays, and integrated in the ReaderBench platform. Several regression models are evaluated in terms of essay scoring accuracy, out of which Gradient Boosting Regression was selected based on its performance (R-2 = .42, MAE = 1.10 on a 10-point scale). The feedback mechanisms provide suggestions for improving the quality of writings based on several rules, which in turn rely on the textual complexity indices computed by the ReaderBench framework, together with meaningful components generated from a Principal Component Analysis.