Advance Personalized Learning is one of the 14 grand challenges of engineering as identified by the National Academy of Engineering. One possible approach for this advancement is to deploy systems that allow an investigator to understand the differences in the learning process of individuals. In this context, cyberlearning systems that use networked computing and communication technology to reach a large number of learners offer the affordance to uniquely identify learners and track their learning process in real-time. Motivated by this idea, this doctoral research aims to investigate personalized learning and engagement within a cyberlearning system, called the Online Watershed Learning System (OWLS). This cyberlearning system utilizes learning resources generated by a real-time high-frequency environmental monitoring system, called the Learning Enhanced Watershed Assessment System (LEWAS).

The goals include advancing the OWLS with a user tracking system and data availability and visualization features and investigating personalized learning and engagement within the OWLS. A user-tracking system is developed utilizing a Node.js-based Express framework and deployed in the LEWAS server, which identifies individual users across devices such as laptops, tablets, and desktops, and detects their interaction within the OWLS, and stores the interaction data in a PostgreSQL database. HTML, CSS, and JavaScript technologies are used for the client-side development. Informed by the situative theory of learning and engagement theory, an investigation was carried out with 52 students from a junior-level civil engineering class. They completed an OWLS-based in-class task focused on concepts related to the environmental monitoring. Pre and post-surveys and the user-tracking system were utilized to collect data on individual student's perceived and conceptual learning, perceived and behavioral engagement, and perception towards the learning value of the OWLS. Results provide several insights into individual student's learning and engagement with the OWLS. For example, students gained knowledge using the OWLS, and their learning varied with the design of the in-class task, which, however, did not impact their engagement. Further, students' learning (scores on in-class task) had a significant negative relationship with their behavioral engagement (frequency of resource utilization of the OWLS). Additionally, temporal navigational strategies of 52 students were identified on an individual basis. Finally, variations in learning and engagement were analyzed in terms of factors such as gender and background knowledge. The study has implications for designing effective cyberlearning systems and learning activities that can utilize cyberlearning systems for leveraging technology-enhanced teaching and learning.