FuzzyQoI model: A fuzzy logic-based modelling of users' quality of interaction with a learning management system under blended learning

Learning management systems (LMSs) in higher education institutions (HEIs) provide the potential for rich learning environments built on social constructivist theories under the concept of blended (b-)learning. An essential factor, however, in determining the efficacy of online teaching–learning is the users' quality of interaction (QoI) with LMSs; yet, in many cases, QoI has not been properly acquired, mainly, due to its inherent qualitative character. Stemming from the latter, this study introduces a new model, namely FuzzyQoI, that, by employing fuzzy logic constructs, it quantitatively estimates the users' (professors' and students') QoI with the LMS Moodle within a b-learning environment. In the FuzzyQoI model, a set of 110 LMS Moodle metrics is considered to form 12 codified inputs to a five-level fuzzy inference system equipped with 600 expert's fuzzy rules. The potential and effectiveness of the realisation of the FuzzyQoI in practice are evaluated from its trialling on LMS data drawn from a large users' database (75 professors and 1037 students), referring to a five-course b-learning process of 51 weeks at a HEI. Experimental results have shown that the proposed FuzzyQoI model efficiently identified (dis)similarities in LMS interaction trends, correlations, distributions and dependencies with the time-period of the LMS use, both for the user-dependent and user-independent (group-like) cases. Consequently, the proposed FuzzyQoI functions as a means for better understanding and explaining the nature of underlying aspects, which influence the users' interaction behaviour under the LMS-based b-learning approach.