Introduction.

Self-regulated learning enables the effective improvement of self-assessment skills and task-selection abilities. However, it is unknown whether technology-supported self-regulation enhances performance in reading comprehension.

Objective.

This research aimed to explore the effectiveness of online self-regulated learning, based on problem-solving tasks, using a selection algorithm applied to reading comprehension.

Method.

The research was an online experimental study conducted with 76 students. They were randomly distributed into two groups: one received training with modeled examples on how to select reading tasks based on the performance and mental effort of previous tasks (i.e., experimental); the other selected tasks based on their preference (i.e., control).

Results.

The ANOVA analysis of the task selection phase data revealed that the experimental group did not achieve a high level of accuracy in task selection, and their performance was low. However, in the subsequent testing phase, the experimental group achieved a higher performance level than the control group.

Discussion.

It is concluded that self-regulated reading comprehension in a technological environment can improve comprehension test results when decision-making is guided by previous performance and cognitive load. The study concludes with recommendations for future research and educational practice.