People have connected with technology in unprecedented ways to solve their learning needs during the COVID-19 learning disruption periods. In New Zealand, tertiary education service providers should seek enhanced ways of supporting learning to face the future of the reformed vocational education system. A recommender system (RS) offers the users information based on their preferences. Kulkarni et al. (2020) have reviewed several RS approaches to improve learning and identified the need for more contributions in the incorporation of this approach into learning services including adaptive learning. In this research, we want to provide customised options to the learners through an adaptive learning solution that uses a content-based RS, which can suggest learning objects (LOs) to the user based on the characteristics of the LOs and user’s preferences. Thus, this research is aimed to answer the following question: How can LOs be presented to learners based on their preferences and learning paths? We used a formal tool, Coloured Petri Nets (CPNs), to specify, validate, and test our proposed system at different levels of abstraction. Interactive graphical and automatic simulations were used to examine behaviour and to debug the model. The results demonstrated the feasibility of our proposal.