A prevailing trend in CSCL literature has been the study of students' participatory roles. The majority of existing studies examine a single collaborative task or, at most, a complete course. This study aims to investigate the presence —or the lack thereof— of a more enduring disposition that drives student participation patterns across courses. Based on data from a 4-year program where 329 students used CSCL to collaborate in 10 successive courses (amounting up to 84,597 interactions), we identify the emerging roles using centrality measures and latent profile analysis (LPA) and trace the unfolding of roles over the entire duration of the program. Thereafter, we use Mixture Hidden Markov Models (MHMM) —methods that are particularly useful in detecting “latent traits” in longitudinal data— to identify how students' roles, transition, persist or evolve over time. Relevant covariates were also examined to explain students’ membership of different trajectories. We identified three different roles (leader, mediator, isolate) at the course level. At the program level, we found three distinct trajectories: an intense trajectory with mostly leaders, a fluctuating trajectory with mostly mediators, and a wallowing-in-the-mire trajectory with mostly isolates. Our results show that roles re-emerge consistently regardless of the task or the course over extended periods of time and in a predictable manner. For instance, isolates “assumed” such a role in almost all of their courses over four years. •Three longitudinal roles in CSCL settings were identified that were homogeneous and relatively stable.•The trajectories were dominated by a certain role: e.g., leaders dominated the intense trajectory.•Roles were likely to re-emerge consistently regardless of the course, e.g., leaders always assumed the role of leaders.•The consistency of longitudinal roles points to a disposition that drives students to assume the same role repeatedly.•A method for studying the longitudinal evolution of student's behavior is described.