MemoryLab logo

Optimizing vocabulary learning: The Impact of MemoryLab’s ‘Quick Skip’ algorithm

Adaptive learning systems are designed to tailor learning experiences to the personal needs of each student. These systems can track and predict student performance, and based on this data, develop personalized repetition schedules of to-be learned material. This can enhance the retention of declarative knowledge, such as vocabulary or toponymy (Lindsey et al., 2014; Papousek et al., 2014). In this text, I demonstrate how MemoryLab’s learning system is able to optimize the learning process of English vocabulary from the EIBO lists.

MemoryLab’s adaptive learning system focuses on improving the long-term retention of declarative knowledge. During learning, when learners encounter a new study item for the first time, they are initially given both the cue and the expected answer. Subsequently, questions are presented that students must answer themselves. The system employs methods such as testing and spaced repetition, based on research in cognitive psychology (van Rijn et al., 2009). It utilizes an Optimal Spacing (OS) algorithm to schedule repetitions of facts based on each student’s accuracy and response times. This ensures that students never spend more time on practicing facts than is necessary.

Efficient time management is desired when learning vocabulary, especially with extensive materials like the contents of the EIBO lists (Engels In het BasisOnderwijs = English In Primary Education). These lists contain English words that students should know before entering secondary school. While valuable, learning these words can be quite time-consuming. Students often spend a lot of time reviewing and repeating the entire vocabulary. Therefore, it is important to find methods that can accelerate and enhance the learning process.

One solution to this is the implementation of MemoryLab’s new ‘Quick Skip’ algorithm. With this algorithm, facts are removed from the repetition schedule of a lesson when they are answered correctly during the initial introduction. During the first presentation of the fact, the correct answer is not shown to the student; this allows us to determine if the student already has prior knowledge of this fact. Once an item is answered correctly at its first presentation, there is no need to continue repeating it. This approach saves up time to practice items that a student not yet fully masters. Research has shown that such an initial attempt to retrieve an answer, even if unsuccessful, positively impacts learning (Wilschut et al., 2024). Actively trying to retrieve information from memory has been demonstrated to enhance learning across diverse subjects, particularly improving long-term retention (Roediger & Butler, 2011).

We aimed to investigate the effect of the new Quick Skip system on learning the extensive EIBO lists. Accordingly we executed a study with first-year students who aimed to focus more on their basic English skills. Twenty students were given the opportunity to practice with a lesson comprising 150 English words. We expected that students with some prior knowledge of the learning material would progress through the lesson relatively fast.

How quickly did the students progress through a list of 150 words?

To investigate this, we examined the speed at which students progressed through the extensive list of 150 English words. Students participated in multiple learning sessions where they had the opportunity to practice with the set of 150 words. Figure 1 illustrates the pace at which students went through the list of 150 words. The y-axis represents the cumulative number of facts covered, while the x-axis shows the overall time spent in the learning sessions. Each line represents the progress of one student, with a dot marking the transition between learning sessions. Ultimately, 5 out of the 20 students practiced all the words. The results clearly demonstrate the effectiveness of the Quick Skip algorithm; students with extensive prior knowledge quickly navigate through the list and get the opportunity to focus on words they haven’t fully mastered yet. For instance, it is evident that one student practiced all 150 words during the first session alone. In earlier versions of our algorithm, learning such a substantial number of facts in this short period of time would not have been possible.

This research demonstrates that MemoryLab’s adaptive learning system, particularly the Quick Skip algorithm, provides an efficient and effective method for learning English vocabulary from the EIBO lists. By minimizing repetitions of already mastered items and shifting focus to items not yet mastered, the system fastens the learning process. Our research showed that students with some prior knowledge of the learning material progressed notably faster through the 150-word lesson, due to the Quick Skip system. These findings underscore the value of adaptive learning methods in speeding up and enhancing the learning of declarative educational material.


Lindsey, R. V., Shroyer, J. D., Pashler, H., & Mozer, M. C. (2014). Improving students’ long-term knowledge retention through personalized review. Psychological science, 25(3), 639–647.

Papoušek, J. & Pelánek, Radek & Stanislav, V.. (2014). Adaptive practice of facts in domains with varied prior knowledge. Proc. of Educational Data Mining. 6-13. 

Roediger, H. L., & Butler, A. C. (2011). The critical role of retrieval practice in long-termretention.Trends in cognitive sciences,15(1), 20–2.

van Rijn, D., van Maanen, L., & van Woudenberg, M. (2009). Passing the test: Improving Learning Gains by Balancing Spacing and Testing Effects. In A. Hoses, D. Peebles, & R. Cooper (Eds.), Proceedings of the 9th International Conference on Cognitive Modeling (pp. 108-114). Article 187.

Wilschut, T., van der Velde, M., Sense, F., Arslan, B., Finn, B., & van Rijn, H. (2024, March 28). Attempted Retrieval Benefits are Limited in Realistic Learning Settings, Unless Used for Prior Knowledge-Based Personalization.

Offerte aanvragen?

Vul het onderstaande formulier in:

Of mail naar:

Aan de slag!

Wilt u meer weten?

Vul het onderstaande formulier in:

Of mail naar: