Adaptive learning refers to a process that utilizes specialized algorithms to create personalized learning paths tailored to the unique needs of each student. In the context of gamification, this approach integrates game-based elements, such as scoring systems, challenges, and rewards, to engage and motivate learners. Technologies like e-learning, m-learning, and blended learning are increasingly being combined with gamification to enhance the educational experience. These systems not only shift from a teacher-centered model to a student-centered one but also transform the learning process into an interactive and engaging experience. While the teacher's role evolves into that of a mentor, guiding students to achieve their maximum potential through intelligent and adaptive technologies, gamification introduces elements of competition and collaboration, further boosting motivation. This article examines adaptive learning systems, such as Knewton and Smart Sparrow, and their integration with gamification techniques to assess knowledge retention, identify gaps, and offer personalized course components, thereby creating a tailored and engaging learning strategy for students.
The rapid advancement of digital technologies has led to significant changes in various fields,
including education. One of the most promising innovations is adaptive learning, which uses
algorithms to customize learning paths according to the unique needs of each student. This approach
not only improves the effectiveness of knowledge acquisition but also helps address individual
learning gaps. In parallel, gamification, which introduces game elements such as rewards, challenges,
and leaderboards into the learning process, has gained popularity as a tool for increasing student
motivation and engagement (Adams Becker et al., 2017) [
Gamification fosters competition, goal setting, and real-time feedback, which enhances learner
engagement and transforms the learning process into a more interactive experience. When combined
with adaptive learning models, gamification can further personalize and enrich the educational
experience, providing tailored and motivating learning environments (Adu & Poo, 2014) [
Adaptive learning systems like Knewton and Smart Sparrow assess students' knowledge levels,
identify gaps, and offer customized content to fill those gaps. By incorporating gamification, these
systems become even more engaging, offering a rewarding and enjoyable learning process
(Henderson, 2014) [
This paper explores the integration of adaptive learning and gamification, presenting a comprehensive review of how these two approaches can create highly personalized and engaging learning experiences, tailored to meet the needs of modern learners.
Thanks to such educational technologies, it is possible to structure the learning process at all stages of student involvement at an advanced level, systematically assessing their subject achievements, and cultivating knowledge, skills, competencies, and capabilities. Furthermore, adaptive learning computer systems act as a type of "mentor" and "counselor" in fostering several critical traits and qualities in students, as well as in developing their essential skills, competencies, and professional abilities.
The primary contributions of this research can be summarized as follows:
The research offers a theoretical foundation for the creation of adaptive learning systems. The research improves students' self-awareness and encourages self-assessment as a method of adaptive learning within the system framework.
The research makes a significant contribution to the literature on adaptive e-learning systems by examining learning effectiveness and satisfaction through empirical studies.
The remainder of the paper is structured as follows: Section II addresses the problem. Section III refers the methodology of adaptive learning model. Section IV reviews the characteristics of existing literature. Section IV outlines the system model of adaptive testing. Section V proposes an algorithm for evaluating student competencies based on adaptive learning. Section VI presents the experimental outcomes and their implementation. Section VII analyzes the results. Finally, Section VIII wraps up the paper.
The integration of adaptive learning models with gamification introduces a series of complex
challenges that impact the overall efficacy and efficiency of educational systems. Adaptive learning is
designed to tailor educational experiences to the specific needs of individual learners, whereas
gamification incorporates elements of game design to enhance engagement and motivation. The
confluence of these approaches necessitates addressing several key issues [
Complexity of Integration: The amalgamation of adaptive learning systems with gamification entails the integration of advanced algorithms and interactive game mechanics into educational platforms. This complexity can pose significant challenges in terms of system design and implementation, requiring that these diverse technologies function cohesively to deliver a unified educational experience.
Overload of Content and Detail: Adaptive learning systems necessitate the provision of extensive and detailed content to effectively personalize the educational experience. When gamified, this content must be managed carefully to prevent cognitive overload. It is imperative to achieve an optimal balance between comprehensive content and engaging presentation to ensure effective learning without overwhelming students.
Frequent Assessment and Feedback: Adaptive learning frameworks rely on continuous assessment to refine and customize the learning experience. The incorporation of gamification elements, such as real-time feedback and rewards, further necessitates frequent evaluations. However, an excessive frequency of assessments or feedback can lead to learner fatigue and potentially diminish the overall effectiveness of the learning process. Ensuring Effective Engagement: While gamification aims to enhance learner engagement through elements such as rewards, challenges, and leaderboards, ensuring that these components are truly effective in sustaining student motivation is a complex task. The design and implementation of gamified elements must be carefully aligned with educational goals to avoid superficial engagement and to ensure meaningful participation.
Data Privacy and Security: The integration of adaptive learning and gamification often involves the collection and analysis of substantial amounts of personal data concerning student performance and preferences. Safeguarding this data and ensuring compliance with privacy regulations is a critical issue that must be addressed to protect student information and maintain trust in the educational system.
Measuring Effectiveness: Evaluating the impact of adaptive learning combined with gamification requires the development of robust metrics and evaluation frameworks. Traditional measures of educational effectiveness may be insufficient to capture the nuances of gamified learning experiences, necessitating the creation of new methodologies to accurately assess the outcomes and benefits of these integrated approaches.
Addressing these issues is essential for maximizing the advantages of combining adaptive
learning with gamification. Solutions must be developed with careful consideration of both
technological and pedagogical factors to enhance the overall efficacy of the educational process [
Below in Fig. 1. the methodology of the adaptive learning algorithm is presented:
Sampling scheme. At this stage a set of modules is formed, consisting of modules
implementing insufficiently studied competencies. Competence Kj is considered
insufficiently studied in two cases. Firstly, if the student has not studied it before, i.e. HRj = ∅.
Secondly, if the competence is lost, i.e. the level of its development, according to the
forgetting curve, has fallen below the Rnorm level over time [
Search P. The genetic algorithm described below is used to find a learning path. Presentation P. The student is provided with the first module from P. The training modules are implemented in the distance learning environment.
Knowledge assessment. Within the framework of the distance learning system a test is formed to check the level of knowledge on the output competencies of the module. Updating S. After the test, the student's current level of knowledge on the history of HRj is updated.
Check the end of the course. The course ends in two cases. First, when the course time expires, i.e. if Ttek ≥ Tkon. Second, if all competencies are studied at a satisfactory level, i.e. KS = K, KF = ∅.We specifically ask workshop organizers to point authors to this requirement in their instructions on the workshop home page.
The Knewton adaptive learning system, established by Jose Ferreira, is discussed in [
Henderson [
Englisch et al. [
The fundamental idea of adaptive learning is to build an optimal trajectory for creating effective
course modules for a student. A module is a logically minimal unit of academic information that can
be presented in various formats such as text, graphics, video, audio, or any other interactive form and
is connected to other units [
F ( PTcon)=TM / R ( Tcon )→ min . (1) where P — is the learning path (the sequence of completing and learning modules), TM — is the maximum time for mastering the modules,
R— is the degree of residual knowledge.
Since the course completion time TconTconTcon is constant, it can be omitted when writing the
objective function (2.1). The objective function involves integer programming, as the array of
learning modules consists of their identifiers represented by integer values. Additionally, the
placement of the problem is quite discretionary: as will be shown later, not all sequences of problem
blocks are suitable. Consequently, taboo problems can only be described in discrete mathematical
terms as relations to sets. Classical optimization algorithms are not suitable for solving such
problems, so genetic algorithms are chosen for this purpose. To extrapolate the remaining level of
knowledge at the end of the course based on the results of intermediate tests, a model based on the
rate of forgetting information is used. No other sufficiently motivated model exists that would
correspond to the numerical prediction of the knowledge level of students who will study in the
future, based on their learning history. The use of Bayesian networks does not provide greater
prediction accuracy (except for adaptive testing functions), but requires significant computational
resources [
In static student modeling is presented in Fig.2, users are allowed to explicitly provide information
to the model. In this approach, the student model is built and updated using information obtained
directly from the user [
In automatic student modeling, information about the user is collected by tracking the user’s
behavior patterns while using the system. The student model can be updated based on preferred
learning content, time spent on content, and answers received from questions or tests [
In the development of an adaptive distance learning system, it is essential to ensure that the
management of the program is as user-friendly as possible to facilitate ease of use for learners [
Below, Figure 3 illustrates the functionalities available to users of the adaptive distance learning system (ADLS) software.
Use case diagrams are an integral tool in the design and analysis of systems, particularly within the context of adaptive learning systems. These diagrams provide a graphical representation of the interactions between users (actors) and the system, specifying the various functionalities or use cases that the system supports. By delineating these interactions, use case diagrams facilitate a clearer understanding of system requirements, user needs, and the overall functionality of the system.
A use case diagram visually represents the functional requirements of a system by illustrating the interactions between actors and use cases. Actors represent external entities that interact with the system, such as students, teachers, or administrators. Use cases are specific functionalities or services provided by the system that fulfill the needs of the actors. The primary purpose of use case diagrams is to capture and document these interactions in a manner that is both comprehensible and actionable.
Use case diagrams are a fundamental tool in the development and analysis of adaptive learning
systems. They provide a structured approach to understanding and documenting system
requirements, facilitating effective design, communication, and validation processes. By accurately
representing the interactions between users and the system, use case diagrams play a crucial role in
ensuring that adaptive learning systems meet the needs of their users and achieve their intended
educational outcomes [
Initially, learners must register in the system. After registration, they can access the question database on their dashboard and begin a test. Learners also have the option to skip a question and return to it later. The system provides a histogram that highlights the learner's strengths and weaknesses. At the end of the test, the system assesses the learner's level and may suggest directions for further skill development based on their initial competencies [19].
Flowcharts are used to visually represent the sequence of steps and decisions required to complete a process. Each step in the sequence is depicted in the form of a diagram. The steps are connected by lines and directional arrows, allowing viewers to logically follow the process from start to finish. A flowchart is a powerful business tool. When designed and constructed correctly, it effectively and efficiently conveys information about the stages of a process. Figure 4 illustrates the algorithm for the program developed for the adaptive distance learning system [20].
gamification with traditional education with elements of An experiment was conducted with adaptive learning involving 10 students studying a single subject using electronic information and an educational environment. Simultaneously, a second group of 12 students studied the same course also using electronic information and an educational environment. However, students in the second group received traditional instruction, with the electronic information and educational environment used solely for the digital presentation of theoretical material in the form of lecture notes and automated knowledge assessment through tests.
While the course content was identical, the methods of content delivery and, consequently, the assessment questions differed. For the second group, the content was uniform for all students, tailored to an average level of educational capability, whereas for the first group, various forms of theoretical material delivery were provided based on the student's assimilation of the material, demonstrating the advantages (or disadvantages) of adaptive learning in terms of students' grasp of the course content. To compare the results, due to the differing group sizes, two students from the second group were randomly excluded. The test results for each group were ordered in ascending order, facilitating visualization and comparison of the outcomes.
The results indicate that students who were taught using the adaptive learning approach achieved higher scores on the final test. Specifically, out of 10 students, four received an "excellent" rating (80100 points), while only 2 students from the traditional model achieved an "excellent" rating. The scores demonstrate that, in the vast majority of cases, students trained with adaptive learning performed better on test questions.
As observed, students undergoing adaptive learning exhibited higher scores. This finding provides practical evidence that adaptive learning is more effective than traditional learning.
This paper explores the concept of adaptive testing within the framework of personalized educational models, aiming to optimize the number of test items presented to students based on their hierarchical skill levels. The adaptive learning model offers a promising solution to address the challenges associated with traditional testing methods, where the “bell curve” effect often leads to a mismatch between the complexity of tasks and individual student abilities. By tailoring test content to each student’s proficiency, adaptive learning models aim to enhance learning outcomes and ensure a more accurate assessment of student capabilities [21].
In contemporary educational settings, adaptive learning systems are increasingly recognized for their ability to dynamically adjust to individual learner differences, thereby facilitating a more personalized learning experience. This study highlights the significance of integrating adaptive learning strategies with e-learning systems, emphasizing the role of theoretical frameworks such as regional forest theory and self-assessment mechanisms. The objective is to improve learning effectiveness by leveraging real-time data to adjust the content and delivery of educational materials in response to student performance [22].
The research presented supports the hypothesis that adaptive learning contributes to better knowledge formation and consolidation by fostering greater student independence, motivation, engagement, and responsibility [23]. The findings are valuable for system developers, educators, and instructional designers, providing insights into the effective implementation of adaptive e-learning environments. Specifically, the results suggest that incorporating adaptive mechanisms and selfassessment tools can significantly enhance the learning experience and outcomes for students [24].
[19] Dalal Abdullah Al Johany, Reda Mohamed Salama, Mostafa Saleh. ASSA: Adaptive E-Learning Smart Students Assessment Model // International Journal of Advanced Computer Science and Applications. – 2018. – 9(7). – 128-136. [20] Z.T. Zhu, D.M. Shen, New paradigm of educational technology research based on Big Data. E
Educ. Res. (10), 5–13 (2013). [21] Z.T. Zhu, J.Q. Guan, The construction framework of “Network Learning Space for Everyone”.
China. Educ. Technol. (10), 1–7 (2013). [22] Pérez-Sánchez, B., Fontenla-Romero, O., & Guijarro-Berdiñas, B. (2018). A review of adaptive online learning for artificial neural networks. Artificial Intelligence Review, 49(2), 281–299. https://doi.org/10.1007/s10462-016-9526-2. [23] Dounas, L., Salinesi, C., & El Beqqali, O. (2019). Requirements monitoring and diagnosis for improving adaptive e-learning systems design. Journal of Information Technology Education: Research, 18, 161-184. https://doi.org/10.28945/4270. [24] Dhakshinamoorthy, A., & Dhakshinamoorthy, K. (2019). KLSAS—An adaptive dynamic learning environment based on knowledge level and learning style. Computer Application in Engineering Education, 27(2), 319–331. https://doi.org/10.1002/cae.22076. [25] Truong, H. M. (2016). Integrating learning styles and adaptive e-learning system: Current developments, prob-lems and opportunities. Computers in Human Behavior, 55(Part B), 1185– 1193. https://doi.org/10.1016/j.chb.2015.02.014.