TAM and stages of adoption of blended learning in higher education by application of data mining techniques

Abstract The purpose of the study is to analyse and identify the stages of adoption of the blended learning (BL or b‐learning) methodology in higher education contexts, and to assess the relationship of these stages with a set of variables related to personal and professional characteristics, attributes perceived on BL and contextual variables. About 980 active academic staff from 43 Spanish public universities participated. The technology acceptance model (TAM) was used as a theoretical framework for the operational definition of the variables. Through the use of data mining techniques (clustering and decision trees), groupings were made based on the b‐learning adoption stage and a subsequent predictive model of these stages. The results show that the intention to use BL is the most important predictor variable in all models applied. In addition, the relationship between higher frequency of use and experience in digital educational environments with higher stages of implementation of the BL methodology was verified. Regarding the socio‐demographic variables included in the study, it was observed that they exert effects that are marginal in all cases. Practitioner Notes What is already known about this topic Many universities and higher education institutions are designing strategic plans and diverse actions to implement and spread the use of BL methodologies. TAM has been widely used to study the behaviour and the intention of using a wide variety of specific technologies in the classroom. The study of BL from the perspective of TAM has generally been carried out using inferential analysis techniques. What this paper adds Analysis of complex systems such as the BL methodology from the TAM approach. Groups of adopting teachers can be analysed using the TAM approach according to the stage of use of this innovation. In contrast to traditional inferential techniques, this paper proposes a methodological procedure based on decision trees, which facilitates a more refined analysis of the relationship and interactions between the set of TAM predictor variables (PU, PEOU, BI, etc.) and the criterion variable (stages of adoption). The obtaining of more complete and adjusted trees leads to better prediction and identification of the concrete actions that could be implemented by higher education institutions as protective or motivating factors for the diffusion of the BL methodology. Implications for practice and/or policy Interest in focusing attention on a complex system such as the one represented by the BL methodology from the perspective of models of technological acceptance reinforces an interesting line of research that can enrich the approach and scope of the TAM theory and generates knowledge that helps promote strategic actions to optimise the institutional diffusion of the BL training modality in higher education contexts.