Adaptive Learning Using Artificial Intelligence in e-Learning: A Literature Review

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

The co-occurrence network reinforces the intertwined relationship between contemporary e-learning platforms, learning systems, and artificial intelligence.

“This co-occurrence network reinforces the intertwined relationship between contemporary e-learning platforms, learning systems, and artificial intelligence.”

Probably not a substantial claim: may not pass S3 (load-bearing).

In [26], neural networks, graph theory, fuzzy sets, classifications, and agent systems were used to create individual learning paths in intelligent learning environments.

“Neural networks, graphs, fuzzy sets, classifications, and agent systems are used as methods in the creation of individual learning paths.”

• cites [26] Afanasyev, A., Voit, N., Voevodin, E., Egorova, T., and Novikova, O. (2014, January 10–12). Methods and tools for the development, implementation and use of the intelligent distance learning environment. Proceedings of the INTED2014 Conference, Valencia, Spain.Not checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [28], the C4.5 decision tree algorithm was used to measure and categorize a learner's knowledge level based on quiz results to personalize the e-learning system.

“The C4.5 decision tree algorithm is used to measure and categorize a learner's knowledge level (e.g., beginner, intermediate, advanced) based on their quiz results.The results then inform the personalization of the e-learning system to cater to the individual needs of the students, which subsequently enhances their knowledge level.”

• cites [28] AL-Chalabi, H.K.M., Hussein, A.M.A., and Apoki, U.C. (2021, January 1–3). An Adaptive Learning System Based on Learner’s Knowledge Level. Proceedings of the 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Pitesti, Romania. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

AI/ML methodologies aid in tailoring content, predicting academic performance, mapping knowledge gaps, and offering dynamic assessments.

“These methodologies aid in tailoring content, predicting academic performance, mapping knowledge gaps, and offering dynamic assessments.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [36], K-means clustering was used to identify and cluster learners based on learning behavior patterns to design personalized online learning environments.

“K-means clustering is used to identify and cluster learners based on their learning behavior patterns, with the aim of understanding and predicting their personalities for the purpose of designing personalized online learning environments.”

• cites [36] Denden, M., Tlili, A., Chang, M., Krahn, T., Kuo, R., Abed, M., and Jemni, M. (2021, January 8–10). Can we predict learners’ personalities through their behavioural patterns? A pilot study using Behaviour Analytics-Moodle plugin. . Proceedings of the 8th International Conference on ICT & Accessibility (ICTA), Tunis, Tunisia. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [39], Bayesian networks and ant colony optimization were used to infer learner features and select and sequence learning objects under time constraints.

“Bayesian networks are used to infer the learner's features based on some input data (probably their interactions or preferences in the e-learning system).Once these features are understood, the system uses the 0/1 knapsack problem to select the best learning objects for the learner in the given time constraint.The ACO algorithm helps to solve this knapsack problem efficiently.”

• cites [39] Haghshenas, E., Mazaheri, A., Gholipour, A., Tavakoli, M., Zandi, N., Narimani, H., Rahimi, F., and Nouri, S. (2010, January 1–2). Introducing a new intelligent adaptive learning content generation method. Proceedings of the Second International Conference on E-Learning and E-Teaching (ICELET 2010), Tehran, Iran. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

In [31], LSTM, random forest classification, and CNNs were used to create a deep learning model for a personalized e-learning system, with random forest predicting learner level and CNN identifying learner style.

“The machine learning algorithms used in the article are long short-term memory (LSTM), random forest classification, and convolutional neural networks (CNNs).The method employed is the creation of a comprehensive model based on deep learning to provide a highly personalized e-learning system.”

• Also stated in: § Citation of Author(s) Algorithm(s)/Method(s) · plain

  “The random forest classifier is used to predict the learner level, which pertains to the difficulty of the course.”

• Also stated in: § Citation of Author(s) Algorithm(s)/Method(s) · plain

  “CNN is used in the identification of the learner style.”

• cites [31] Anantharaman, H., Mubarak, A., and Shobana, B.T. (2018, January 21–22). Modelling an Adaptive e-Learning System Using LSTM and Random Forest Classification. Proceedings of the IEEE Conference on e-Learning, e-Management and e-Services (IC3e), Langkawi, Malaysia. sourceNot checked yet

  Not checked in the free run.

The quote only partly states this claim.

In [23], supervised learning algorithms (SVMs, kNN, Naïve Bayes, random forest, logistic regression) were used to predict learner personality dimensions from educational data features in an online learning system.

“The system focuses on developing a classifier based on supervised learning algorithms to predict the learner's personality dimensions discreetly using educational data features in an online learning system.”

• cites [23] Abyaa, A., Idrissi, M.K., and Bennani, S. (2018, January 24–25). Predicting the learner’s personality from educational data using supervised learning. Proceedings of the 12th International Conference on Intelligent Systems: Theories and Applications (SITA’18), Rabat, Morocco. Article 19. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

Disagreements among reviewers were deliberated and resolved after removal of the blinded protocol, leading to unanimous consensus.

“Disagreements among reviewers were deliberated and resolved following the removal of the blinded protocol, leading to a unanimous consensus among all authors regarding the final decision on inclusion or exclusion of articles.”

Probably not a substantial claim: may not pass S3 (load-bearing).

In [34], chatbots using ML algorithms were used to analyze learner requirements and generate personalized learning paths with tailored content.

“The application of ML algorithms is used to analyze each learner's personal requirements and generate a corresponding personalized learning path with tailored educational content.”

• cites [34] Shkarlet, S., Morozov, A., and Palagin, A. (2021). Mathematical Modeling and Simulation of Systems (MODS’2020); MODS 2020 Advances in Intelligent Systems and Computing, Springer. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Reinforcement learning (RL) is employed to optimize learning paths and learning objects using implicit feedback from learners.

“• Reinforcement learning (RL) is employed to optimize learning paths and learning objects using implicit feedback from learners.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Rapid adaptation of learner models is a perceived benefit of using AI/ML to power adaptive learning in e-learning systems.

“• Rapid adaptation of learner models.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Genetic algorithms map optimal individualized learning paths.

“• Genetic algorithms map optimal individualized learning paths.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

Dynamic recommendations of supplementary materials are a perceived benefit of using AI/ML to power adaptive learning in e-learning systems.

“• Dynamic recommendations of supplementary materials.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Logistic regression, SVM, ARIMA, deep neural networks, and RNNs are combined to enhance and customize the learning environment.

“• Logistic regression, SVM, ARIMA, deep neural networks, and RNNs are combined to enhance and customize the learning environment.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

In [30], latent semantic analysis and fuzzy C-means were used to extract metadata from learning objects and identify learning objects based on similarity.

“LSA is used to extract metadata from learning objects (LOs).LSA is a technique that finds patterns in relationships between terms and concepts in unstructured data, mainly used for analyzing relationships in a set of documents.Fuzzy C-means (FCM) algorithms: FCM is used to identify learning objects based on a specific form of similarity.”

• cites [30] Amane, 2023, New perspective of learning objects in e-learning system, Int. J. Inf. Learn. Technology. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Efficient clustering of learners for tailored strategies is a perceived benefit of using AI/ML to power adaptive learning in e-learning systems.

“• Efficient clustering of learners for tailored strategies.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Two-stage Bayesian functions as a recommendation system, customizing learning materials.

“• Two-stage Bayesian functions as a recommendation system, customizing learning materials.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [27], ant colony optimization was used to optimize learning paths for groups of students based on their knowledge patterns.

“The ACO algorithm is used to optimize learning paths for different groups of students.The first stage involves grouping learners based on their knowledge patterns.The second stage then uses the ACO algorithm to determine the best learning path for each of these groups, with the end goal being a concept map tailored to the needs of each group.”

• cites [27] Ahmad, K., Maryam, B.I., and Molood, A.E. (2013, January 13–14). A novel adaptive learning path method. Proceedings of the 4th International Conference on e-Learning and e-Teaching (ICELET 2013), Shiraz, Iran. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [37], machine learning within the LearnFit framework was used to personalize and adapt learning paths using learning style models and learner profiles.

“Machine learning is used in this article to apply machine learning techniques within the LearnFit framework to personalize and adapt the learning paths for learners.”

• cites [37] Berrada, K., and Burgos, D. (2022). Pedagogy, Didactics and Educational Technologies, Springer. Lecture Notes in Educational Technology. sourceNot checked yet

  Not checked in the free run.

May combine two claims.

Adaptive learning has the potential to revolutionize education by catering to individual learner needs, despite challenges like data privacy and complexity of AI/ML systems.

“Despite challenges like data privacy and the complexity of AI/ML systems, the results underscore the potential of adaptive learning to revolutionize education by catering to individual learner needs.”

• AssumptionRests on an assumption: The 63 included articles are representative of the current deployment of AI/ML in e-learning for adaptive learning.

Classified as probably not a substantial claim.

Personalized learning experiences and pathways are a perceived benefit of using AI/ML to power adaptive learning in e-learning systems.

“• Personalized learning experiences and pathways.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [40], an optimized K-means clustering algorithm was used to cluster learners in MOOC forums and aid instructors in designing personalized learning strategies.

“An optimized version of the K-means clustering algorithm, an unsupervised learning method, is used to efficiently cluster learners in MOOC (massive open online course) forums and aid instructors in designing personalized learning strategies.”

• cites [40] Hou, X., Lei, C.-U., and Kwok, Y.-K. (2017, January 18–21). OP-DCI: A Riskless K-Means Clustering for Influential User Identification. Proceedings of the 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, Mexico. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Q-learning recommends adaptive learning paths.

“• Q-learning recommends adaptive learning paths.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

In [32], evolutionary algorithm, ant colony optimization, and social network analysis were used to determine future educational objectives, generate adaptive learning paths, and assign learning rhythm.

“Evolutionary algorithm used for determining relevant future educational objectives using an adequate learner e-assessment method.ACO is used for generating an adaptive learning path for each learner.SNA is used for determining the learner's motivation and social productivity to assign a specific learning rhythm to each learner.”

• cites [32] Birjali, 2018, A novel adaptive e-learning model based on Big Data by using competence-based knowledge and social learner activities, Appl. Soft Comput. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Conditional generative adversarial networks (cGANs) adapt a model of the learner's characteristics to simulate performance and improve training.

“• Conditional generative adversarial networks (cGANs) adapt a model of the learner's characteristics to simulate performance and improve training.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

K-means clustering is used to cluster learners in MOOC forums, segment datasets based on similarity, and identify learning behavior patterns.

“• K-means clustering is used to cluster learners in MOOC forums, segment datasets based on similarity, and identify learning behavior patterns.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [24], DBSCAN was used to process learners' contextual information from mobile devices to group learners and provide personalized, adaptive guidance.

“DBSCAN is used to process the learners' contextual information extracted from their mobile devices.It is likely being used to group or categorize learners based on their contextual information such as background knowledge, learning time, learning location, and environmental situation.”

• cites [24] Adnan, 2019, Cloud-supported machine learning system for context-aware adaptive M-learning, Turk. J. Electr. Eng. Comput. Sci. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

Light gradient boosting machine (LGBM) identifies learning styles and predicts academic performance.

“• Light gradient boosting machine (LGBM) identifies learning styles and predicts academic performance.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

Optimized learning paths and objects are a perceived benefit of using AI/ML to power adaptive learning in e-learning systems.

“• Optimized learning paths and objects.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [25], a linearization algorithm generated a suggested learning path for students based on the Educational Concept Map to personalize learning materials.

“The linearization algorithm generates a suggested learning path for students based on the Educational Concept Map (ECM).The algorithm is used to personalize the learning materials and educational resources for each student based on their self-evaluation of knowledge and learning objectives.”

• cites [25] Adorni, G., Cagnoni, S., Gori, M., and Maratea, M. (2016). AI*IA 2016 Advances in Artificial Intelligence, Springer. AI*IA 2016 Lecture Notes in Computer Science. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

In [33], genetic algorithm with forcing legality and particle swarm optimization were used to create personalized e-courses by selecting appropriate e-learning materials from a database.

“The algorithm is utilized for creating personalized e-courses in adaptive learning systems.The goal is to efficiently select appropriate e-learning materials from a database tailored to individual learners.”

• cites [33] Chang, 2013, A personalized e-course composition based on a genetic algorithm with forcing legality in an adaptive learning system, J. Netw. Comput. Appl. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

Heterogeneous value difference metric (HVDM) and naïve Bayes classifier (NBC) provide adaptive learning support by measuring similarity between learners and predicting their needs.

“• Heterogeneous value difference metric (HVDM) and naïve Bayes classifier (NBC) provide adaptive learning support by measuring similarity between learners and predicting their needs.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

Enhanced recommendation systems and targeted learning material delivery are perceived benefits of using AI/ML to power adaptive learning in e-learning systems.

“• Enhanced recommendation systems and targeted learning material delivery.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Collaborative filtering (CF) constructs personalized learning platforms.

“• Collaborative filtering (CF) constructs personalized learning platforms.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Deep learning (DL) analyzes students' learning situations, providing targeted resources.

“• Deep learning (DL) analyzes students' learning situations, providing targeted resources.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

May combine two claims.

Immediate feedback helps learners understand their mistakes, make corrections, and reinforce their understanding, facilitating a more efficient learning process.

“This immediate feedback helps learners understand their mistakes, make corrections, and reinforce their understanding, facilitating a more efficient learning process [88].”

• cites [88] Phon-Amnuaisuk, S., Au, T.W., and Omar, S. (2017). Computational Intelligence in Information Systems, Springer. CIIS 2016 Advances in Intelligent Systems and Computing. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

The selection of keywords to compile the publication samples may not be exhaustive, potentially missing pertinent studies.

“Firstly, the selection of keywords to compile the publication samples may not be exhaustive, potentially missing out on pertinent studies.”

May combine two claims.

Adaptive e-learning platforms powered by AI/ML algorithms can track and analyze learner performance, identify knowledge gaps, and offer remedial content or activities to address those gaps.

“Improved Learning Outcomes: Adaptive e-learning platforms powered by AI/ML algorithms can track and analyze learner performance, identify knowledge gaps, and offer remedial content or activities to address those gaps.”

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

The integration of AI/ML, particularly adaptive learning algorithms, stands as a pillar influencing key sectors from personalized learning experiences to intelligent recommendation systems.

“In the realm of e-learning, the integration of AI/ML, particularly adaptive learning algorithms, stands as a pillar influencing key sectors from personalized learning experiences to intelligent recommendation systems.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Clear inclusion and exclusion criteria were established to minimize potential bias in the selection of studies.

“To minimize potential bias in the selection of studies, clear inclusion and exclusion criteria are established.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Adaptive learning systems can enhance student engagement, foster self-directed learning, and improve overall learning outcomes by leveraging data-driven personalization, timely feedback, and dynamic content delivery.

“By leveraging the power of datadriven personalization, timely feedback, and dynamic content delivery, adaptive learning systems can enhance student engagement, foster self-directed learning, and improve overall learning outcomes.”

May combine two claims.

The research query was framed exclusively in English, so it omits any resource published solely in other languages.

“Additionally, since our research query was framed exclusively in English, it inherently omits any resource published solely in other languages.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Tools discussed in analytical summaries, conferences, or developer hackathons were not considered for this study.

“Such tools might be discussed in analytical summaries, showcased in conferences, or highlighted during developer hackathons, all of which were not considered for this study.”

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

AI/ML algorithms can analyze learner interactions, group dynamics, and social network data to provide personalized recommendations for group projects, collaborative learning activities, and peer feedback.

“AI/ML algorithms can analyze learner interactions, group dynamics, and social network data to provide personalized recommendations for group projects, collaborative learning activities, and peer feedback.”

Probably not a substantial claim: may not pass S2 (checkable), S4 (based). May combine two claims.

The flexibility and adaptability of content delivery ensure that students receive the most up-to-date and relevant information, making their learning experiences more meaningful and effective.

“The flexibility and adaptability of content delivery ensure that students receive the most up-to-date and relevant information, making their learning experiences more meaningful and effective.”

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

Proper referencing and citation practices were followed to avoid plagiarism and respect intellectual property rights, and all sources are appropriately cited and credited.

“Proper referencing and citation practices are followed to avoid plagiarism and respect the intellectual property rights of the original authors.”

• Also stated in: § 6. Ethical Considerations · plain

  “All sources used in the literature review are appropriately cited and credited, following established citation styles.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Need for ongoing training and updates to machine learning models is a challenge educators and developers face when integrating AI/ML into e-learning platforms for adaptive learning.

“• Need for ongoing training and updates to machine learning models.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

Explainable AI helps people understand how and why models give certain recommendations.

“Explainable artificial intelligence mitigates to help people to understand how and why models give certain recommendations [90].”

• cites [90] Miller, T. (2023, January 12–15). Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven Decision Support using Evaluative AI. Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (FAccT ‘23), Chicago, IL, USA. sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Identification of learning styles for improved academic predictions is a perceived benefit of using AI/ML to power adaptive learning in e-learning systems.

“• Identification of learning styles for improved academic predictions.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Harnessing machine learning in e-learning systems unlocks a spectrum of benefits, central to which is the creation of highly personalized educational journeys.

“Harnessing the power of machine learning in e-learning systems unlocks a spectrum of benefits, central to which is the creation of highly personalized educational journeys.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

The actual array of educational tools may be broader and more varied than presented.

“This implies that the actual array of tools may be broader and more varied than presented.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Critical evaluation and transparent reporting of the review process were carried out to ensure objectivity in synthesis and reporting.

“Critical evaluation and transparent reporting of the review process are carried out to ensure objectivity in the synthesis and reporting of the results.”

Probably not a substantial claim: may not pass S3 (load-bearing). The quote only partly states this claim.

Cold-start problems, where systems have little initial data on learners, are a challenge educators and developers face when integrating AI/ML into e-learning platforms for adaptive learning.

“• Cold-start problems, where systems have little initial data on learners.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Adaptive learning driven by AI/ML enhances the learning experience by clustering similar learners.

“• Enhances the learning experience by clustering similar learners.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Adaptive learning driven by AI/ML predicts student performance using learning styles.

“• Predicts student performance using learning styles.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S4 (based).

Adaptive learning driven by AI/ML improves personalization through targeted material delivery.

“• Improves personalization through targeted material delivery.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Adaptive learning driven by AI/ML focuses on optimal learning activities based on learner profiles.

“• Focuses on optimal learning activities based on learner profiles.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

May combine two claims.

Adaptive e-learning systems engage and encourage learners by adding features like gamification and tailored information, which can increase student motivation and drive, leading to improved learning outcomes.

“These systems engage and encourage learners by adding features like gamification and tailored information, which can increase student motivation and drive, leading to improved learning outcomes [89].”

• cites [89] Greene, R.T. (2023, May 12). The Future of Instructional Design: Engaging Students Through Gamified, Personalized, and Flexible Learning with AI and Partnerships; e-Learning Industry. Available online: https://elearningindustry.com/future-of-instructional-design-engaging-students-through-gamified-personalized-flexible-learning-with-ai-and-partnerships.Not checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

Since this literature review involves analyzing previously published works, obtaining informed consent from human participants is not applicable.

“Informed consent: Since this literature review involves analyzing previously published works, obtaining informed consent from human participants is not applicable.”

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Adaptive learning driven by AI/ML provides real-time assistance through chatbots.

“• Provides real-time assistance through chatbots.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

These technologies can analyze vast repositories of educational resources, adaptively recommend relevant content based on individual learner profiles, and generate customized learning materials.

“These technologies can analyze vast repositories of educational resources, adaptively recommend relevant content based on individual learner profiles, and even generate customized learning materials.”

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

The integration of machine learning into e-learning platforms comes with challenges including initial data scarcity, complexities in amalgamating AI/ML techniques, data privacy concerns, and potential algorithmic biases.

“From the hurdles of initial data scarcity and complexities in amalgamating AI/ML techniques, to looming concerns of data privacy and potential algorithmic biases, educators and developers must tread carefully.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Developing, integrating, and maintaining AI-driven systems can be expensive.

“• Developing, integrating, and maintaining AI-driven systems can be expensive.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

Data privacy concerns in collecting and analyzing student data can raise privacy issues.

“• Data privacy concerns in collecting and analyzing student data can raise privacy issues.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

Not all relevant educational tools were documented in research papers listed in reference databases.

“Moreover, there is a likelihood that not all relevant educational tools were documented in research papers listed in reference databases.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

This individualized approach enhances engagement, motivation, and knowledge retention, ultimately leading to improved academic performance.

“This individualized approach enhances engagement, motivation, and knowledge retention, ultimately leading to improved academic performance.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Adaptive e-learning is increasingly incorporating collaborative and social learning components.

“Adaptive e-learning is increasingly incorporating collaborative and social learning components.”

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

Chatbots, voice assistants, and natural language-based assessment and feedback systems can enhance conversational and personalized learning experiences.

“This includes chatbots, voice assistants, and natural language-based assessment and feedback systems that can enhance conversational and personalized learning experiences.”

Classified as probably not a substantial claim. May combine two claims.

Data-driven decision making facilitates targeted interventions and allows for continuous improvement of the e-learning environment.

“Such data-driven decision making not only facilitates targeted interventions but also allows for continuous improvement of the e-learning environment.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Complexity of combining multiple machine learning techniques is a challenge educators and developers face when integrating AI/ML into e-learning platforms for adaptive learning.

“• Complexity of combining multiple machine learning techniques.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing).

The literature review employed a comprehensive search strategy inclusive of various databases and sources to minimize potential bias in selection of studies.

“A comprehensive search strategy, inclusive of various databases and sources, is employed to minimize potential bias in the selection of studies.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Adaptive learning aligns closely with the diverse needs and styles of learners and drives favorable outcomes in key educational metrics by delivering tailored content, real-time feedback, and optimizing the learning journey according to individual learner profiles.

“By delivering tailored content and real-time feedback, and by optimizing the learning journey according to individual learner profiles, this modern pedagogical approach aligns closely with the diverse needs and styles of learners, thereby driving favorable outcomes in key educational metrics.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

AI and ML capabilities allow these systems to analyze large volumes of data, identify patterns, and generate actionable insights for both students and instructors.

“By leveraging AI and ML capabilities, these systems can analyze large volumes of data, identify patterns, and generate actionable insights for both students and instructors.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Features of adaptive learning driven by AI/ML potentially increase engagement, retention, and performance by offering tailored content, real-time feedback, and optimal learning pathways.

“• Such features potentially increase engagement, retention, and performance by offering tailored content, real-time feedback, and optimal learning pathways.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S4 (based).

Integration of AI and ML in e-learning opens up opportunities for dynamic content generation and usage.

“Moreover, the integration of AI and ML in e-learning opens up opportunities for dynamic content generation and usage.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Adaptive learning systems provide real-time feedback and progress tracking, enabling educators to identify students' areas of struggle and intervene promptly.

“Furthermore, adaptive learning systems provide real-time feedback and progress tracking, enabling educators to identify students' areas of struggle and intervene promptly.”

Probably not a substantial claim: may not pass S4 (based).

By analyzing individual learners' strengths, weaknesses, and learning styles, AI and ML algorithms can adapt content, pace, and delivery methods to optimize learning outcomes.

“By analyzing individual learners' strengths, weaknesses, and learning styles, AI and ML algorithms can adapt the content, the pace, and the delivery methods to optimize learning outcomes.”

Classified as probably not a substantial claim. May combine two claims.

A comprehensive search across multiple databases and sources was conducted, and the selection process was documented to provide transparency and a clear rationale for inclusion/exclusion.

“A comprehensive search across multiple databases and sources is conducted, and the selection process is documented to provide transparency and a clear rationale for the inclusion or exclusion of specific studies.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Adaptive learning powered by machine learning leads to heightened engagement, bolstered retention, and enhanced performance.

“Adaptive learning, powered by machine learning, profoundly reshapes the educational landscape, leading to heightened engagement, bolstered retention, and enhanced performance.”

Probably not a substantial claim: may not pass S4 (based). May combine two claims.

Adaptive learning driven by AI/ML improves test scores and overall academic performance.

“• Improve test scores and overall academic performance.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.

Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

AI-powered systems can process and understand human language, enabling more advanced interactions with learners.

“AI-powered systems can process and understand human language, enabling more advanced interactions with learners.”

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

Over-reliance on technology carries a risk of neglecting the human aspect of education.

“• Over-reliance on technology-there is a risk of neglecting the human aspect of education.”

• AssumptionRests on an assumption: The reviewed studies' reported algorithm usages, benefits, challenges, and impacts are accurate and applicable to e-learning adaptive learning.