Comparing AI-enhanced instructional designs for EFL postgraduate proficiency: a multisite randomized controlled trial with exploratory ICC outcomes

This project explored the feasibility of implementing an innovative cross-curricular framework using an adaptive learning (AL) platform and telehealth simulations. To determine the feasibility of implementing an innovative cross-curricular framework using an AL platform and telehealth simulations. A mixed-method pilot study was conducted using novel AL modules, adaptive case studies, and telehealth simulation. Quantitative data analysis demonstrated significant correlations within and across demographics using the Technology Acceptance Model (TAM) and Simulation Effectiveness Tool-Modified (SET-M). Specifically, significant correlations are evident between TAM ease of use items 1-6, 8, and 10 and TAM usefulness 1, 3, and 9, with SET-M items 3 and 5-15. Thematic analysis revealed that participants felt that the overall project was worthwhile and increased confidence in telehealth. Participants found the technology used in this study was easy and useful, and they indicated a positive experience with telehealth simulation. Overall, this study demonstrated that implementation of AL using our paradigm is feasible and supports further investigation into implementing a cross-curricular framework using an AL platform and telehealth simulations.

There is a great deal of excitement in higher education about the value of adaptive learning to personalize learning paths according to students' individual needs. The authors explored the impact of an Adaptive Learning Platform (ALP) on learning, by comparing learning effectiveness between dental students who used the ALP in a blended learning environment formatively and summatively compared with students who did not use the ALP (i.e., face-to-face), as measured by students' performance on the final exam in a single review preparatory course during the academic years 2013-2018. Paired t-tests showed significant improvement in post-test scores across different course instructional modalities (P < 0.01). The learning gain was greater for students who studied using the ALP summatively (t = 26.20) than those who used it formatively or studied using a face-to-face format (t = 13.10 and 14.13, respectively). Controlling for pre-test scores, analysis of covariance tests indicate that: (1) intervention groups (formative and summative ALP) scored significantly higher than the traditional group (B = 9.34 points, P < 0.01, for summative ALP group) and (B = 4.47 points, P < 0.05, for formative ALP group), and (2) summative ALP group scored significantly higher than formative ALP group (B = 4.84 points, P < 0.05). This study provides empirical evidence that an adaptive learning intervention can have a significant impact on student learning performance. The success of any adaptive learning system relies mainly on sound instructional design. Technology will continue to grow at an overwhelming pace; the cautionary note the authors highlight is that conceptions of pedagogy, complemented by technology, must guide the development of adaptive learning systems.

Adaptive learning platforms are increasingly being used as part of varying instructional modalities. Particularly relevant to this paper, adaptive learning is a critical component of personalized, preclass learning in a flipped classroom. Previously inaccessible, data generated by adaptive learning platforms regarding student engagement with the course content provides an invaluable opportunity to gain a deeper understanding of the learning process and improve upon it. We aim to investigate the relationships between adaptive learning platform interactions and overall student success in the course and identify the variables most influential to student success. We present a comprehensive analysis of our adaptive learning platform data collected in a Numerical Methods course, including aggregate statistics, frequency analysis, and Principal Component Analysis, to determine which variables exhibited the most variability and, therefore, the most information in the data. Subsequently, we used the Partitioning Around Medoids clustering approach to investigate naturally occurring clusters of students and how these clusters relate to overall performance in the course. Our results show that overall performance in the course, as measured by the final course grade, is strongly associated with (1) the behavioral interactions of students with the adaptive platform and (2) their performance on the adaptive learning assessments. We also found distinct student clusters (as defined by success in the course) that exhibited distinctly different behaviors. These findings provide qualitative and quantitative information to identify students needing support and to craft an evidence‐based support strategy for these students.

In a Fall 2017 introductory course in Environmental Geology, homework assignments alternated between traditional textbook chapters in an electronic format and adaptive learning platform (ALP) modules on the Smart Sparrow (www.smartsparrow.com) platform to assess student preference for and satisfaction with either modality. Few studies have evaluated the role of ALP technology in a classroom setting, and none have investigated ALPs in a homework setting. To probe student preferences between these assignments, and their engagement with the material through the different modalities, all (n = 17) students in the course were given eight surveys over the Fall 2017 semester. A subset of six students volunteered for qualitative interviews in addition to the quantitative surveys. Analysis of the results shows that students were more satisfied with the ALP modules, except for the longest assigned module. No relationships were found between preference for one module over another and major, engagement, or interest in environmental geology. A majority of the students interviewed identified the interactivity of the adaptive learning modules as a contributing factor to the retention of concepts presented. This suggests students experienced a higher level of cognitive engagement with the ALP material.

How Can Adaptive Platforms Improve Student Learning Outcomes? A Case Study of Open Educational Resources and Adaptive Learning Platforms

Adaptive learning platforms that individualize each learner's experience according to their input have only recently become widely accessible. This chapter illustrates some of the potential of adaptive learning platforms and describes a case study where this emerging technology has been used with physiotherapy students in a simulated clinical setting. Aspects of patient care scenarios presented with an adaptive learning platform were interleaved with live simulated patient interactions. Evaluation of the projects and the benefits and challenges of using adaptive learning platforms in biomedical education are discussed.

This study investigates the impact of Pearson’s MyLab adaptive learning platform on student performance in an Introductory Microeconomics course at a private university in Kuwait. The study examined the association between Pearson’s adaptive learning platform scores and student performance on midterm and final exams. Using a random-effects generalized least squares regression model, the analysis revealed that Pearson’s adaptive learning platform improves student performance. The importance of self-regulated learning over gender and seniority was also noted. Future research should include a broader range of universities and explore the utilization levels of adaptive learning tools to enhance understanding of their effectiveness.

Recent technological advancements have led to various educational innovations, including adaptive Learning, which customizes content and instructional methods to meet the diverse needs and abilities of individual students. Several empirical studies have utilized adaptive learning platforms to support differentiated Learning in science. However, to date, there has yet to be a comprehensive review of the findings in this area. This study aims to explore research trends related to differentiated Instruction through adaptive learning platforms in science education, as documented in Scopus-indexed journal articles published between 2019 and 2024. The research follows PRISMA guidelines, employing the Publish or Perish application for the search system, with data sourced from SCOPUS. The search yielded 368 articles, and screening based on specific inclusion and exclusion criteria resulted in 23 papers that were subsequently analyzed. This study highlights various adaptive technology methods used in science education, emphasizing Learning Management Systems (LMS) and Artificial Intelligence (AI). LMS emerges as the most frequently utilized, followed by AI and assessment platforms. Crucial factors for successful implementation include real-time feedback and accessibility to technology. Although these platforms improve learning outcomes, issues regarding student engagement and satisfaction persist. Educational institutions should assess their technological infrastructure and provide training for educators to leverage new features effectively. Additionally, developers should focus on enhancing personalization options, while further research is necessary to address students' emotional needs better and enhance their motivation. Keywords: adaptive learning, differentiated instruction, science education, teaching, systematic literature review. DOI: http://dx.doi.org/10.23960/jpmipa/v25i2.pp914-931

Personalised, adaptive online learning platforms that form part of web-based proficiency tests play a major role in the improvement of the quality of learning in physics and assist learners in building proficiency, preparing for tests and using their time more effectively. In this study, the effectiveness of an adaptive learning platform, Wiley Plus ORION, was evaluated using proficiency test scores compared to paper-based test scores in a first-year introductory engineering physics course. Learners’ performance activities on the adaptive learning platform as well as their performance on the proficiency tests and their impact on the paper-based midterm averaged test were investigated using both qualitative and quantitative methods of data collection. A comparison between learners’ performance on the proficiency tests and a paper-based midterm test was done to evaluate whether there was a correlation between their performance on the proficiency tests and the midterm test. Focus group interviews were carried out with three categories of learners to elicit their experiences. Results showed that there was a positive relationship between high-performing learners’ proficiency score in the midterm averaged test and that the proficiency test enhanced learners’ performance in the paper-based midterm averaged test.

Along with the growing popularity of the adaptive learning platform software in STEM education programs, further enhancing the ability of the adaptive learning platform to support learning effectiveness has become a priority. A common goal of all the adaptive learning platform software is to identify gaps in a student's knowledge, and provide relevant learning materials based on the result of the assessment of the student's exiting knowledge towards to the targeted subject, to increase the learning effectiveness. However, the student's existing knowledge is only one learning attribute, and it cannot reflect all the aspects that have an impact to the student's learning effectiveness. A natural solution to overcome this weakness is to make the adaptive learning decision making algorithm capable to process the dataset of multiple learning attributes of the student efficiently. This paper presents a machine learning algorithm to efficiently process the dataset of a student's multiple learning attributes. The main enabling foundation for this new algorithm is a data structure called “student learning attributes index” which represents every learning attribute as a tuple of three elements: the “learning-attribute-If)”, the “weight” of the learning attribute among all the learning attributes, and the “efficiency” of the contribution to the student's learning effectiveness made by the learning attribute. This study has applied unequal weight to each of the learning attributes, more accurately reflecting that different learning attributes will have different impacts on a student's learning effectiveness. This new algorithm enables various learning support applications to become more practical and accurate in supporting student learning.

Cancer Genomics in Clinical Context

The Smart Study Buddy is an innovative AI-driven, web-based adaptive learning platform that redefines how students interact with and internalize academic content in the digital age. Built upon the convergence of machine learning (ML), natural language processing (NLP), and human-centered design, the system intelligently processes raw study materials—such as notes, lecture slides, research papers, and textbooks—to generate structured, context-aware learning outputs. These include automatically generated summaries, interactive quizzes, flashcards, crossword-style exercises, and keyword extractions, all aimed at enhancing comprehension, retention, and recall efficiency. At its core, Smart Study Buddy employs transformer-based deep learning models (GPT-2 and fine-tuned BERT architectures) to extract semantic meaning from unstructured text and produce concise, accurate summaries that maintain conceptual integrity. The quiz generation module leverages NLP-driven question-answering techniques to produce multiple-choice, true/false, and short-answer questions from the summarized content, encouraging active recall, which is a proven method for long-term memory consolidation. In parallel, the flashcard module and adaptive scheduling system promote spaced repetition, helping learners review difficult topics at optimal intervals based on past performance and engagement metrics. The platform architecture integrates a Python and Streamlit-based front-end interface for real-time interactivity, a SQL-backed database for persistent user data management, and OpenAI’s GPT API for semantic processing. The adaptive scheduler dynamically adjusts daily learning goals using predictive analytics to prevent cognitive overload and improve time management. The progress dashboard visualizes study trends, accuracy rates, and content mastery through analytics charts, while gamification elements such as points, streaks, and badges foster intrinsic motivation and consistent participation. Furthermore, the system features an AI-powered “Chat with Notes” assistant, allowing users to ask natural-language questions about their uploaded materials and receive contextually relevant explanations derived directly from their study corpus. This feature bridges the gap between passive content review and active conversational learning, simulating the experience of an intelligent personal tutor. Smart Study Buddy not only minimizes the effort required for manual summarization, note-making, and quiz creation but also enhances personalized learning through continuous feedback loops and intelligent progress evaluation. By incorporating AI personalization, behavioral analytics, and gamified engagement, it transforms traditional study methods into an adaptive, data-driven, and self-evolving learning ecosystem. Ultimately, this research demonstrates how AI-assisted educational platforms can foster autonomous learning, improve academic performance, and significantly reduce time spent on content preparation. The Smart Study Buddy exemplifies the future of intelligent education systems—an intersection of technology, pedagogy, and psychology—empowering learners to achieve higher efficiency, deeper understanding, and sustained motivation in an ever-expanding information landscape. .. Keywords: Artificial Intelligence · Adaptive Learning · Educational Technology · GPT-2 · Machine Learning · Natural Language Processing · Summarization · Quiz Generation · Flashcards · Gamification · Streamlit · Personalized Study Assistant · Cognitive Computing · Academic Automation

At present a large number of learning platforms are the accumulation of educational resources. In the face of chaotic educational resources, learners become overwhelmed and unable to find their own resources effectively. Adaptive learning platform aims to build learning environment and provide learning objects based on learner’s individualized information usage behavior, habits, preferences and etc. It can guide learner’s learning activities as a teacher, and enhance learning efficiency. This paper presents an ontology and sequence mining based selection method for learning objects and learning tools in adaptive learning platform. It mines the learning scheme through the sequence mining method to achieve personalized learning scheme. Besides, according to the learning scheme, it integrates the existing e-learning tools to build learning environment by service composition method, and aggregation all the related learning objects into learning content by using ontology technology to describe the semantic relationship between learning objects.KeywordsLearning Object OntologySequence MiningService CompositionAdaptive Learning Platform

Abstract—In the current competitive placement landscape, tra- ditional learning platforms fail to provide personalized, adaptive, and reliable assessment mechanisms, leading to inefficient prepa- ration and poor skill evaluation. This paper presents Skillatics, an AI-driven adaptive learning and assessment platform designed to enhance student placement readiness through a unified and data-driven approach. The system integrates an adaptive test engine that dynamically adjusts question difficulty based on real- time student performance, ensuring personalized learning paths. It also incorporates a secure, sandboxed coding environment using containerized execution for technical assessments, along with a lightweight proctoring system to maintain academic integrity. Furthermore, an AI-powered analytics module identifies topic-wise skill gaps and provides actionable feedback, enabling targeted improvement. To enhance engagement, the platform includes gamification features such as experience points, leader- boards, and interactive learning modes. The proposed system is implemented as a scalable web-based application using modern technologies including React, Flask, MongoDB, and external APIs such as Piston and Google Gemini. The results demonstrate that integrating adaptive learning, secure assessment, and analytics into a single platform significantly improves learning efficiency, engagement, and overall placement preparedness. Index Terms—Adaptive Learning Systems, AI-Based Learning Analytics, Skill Gap Analysis, Coding Assessment Platforms, On- line Proctoring Systems, Gamification in Education, Placement Preparation Systems

This Research to Practice Work in Progress paper presents the design of personalized learning modules on adaptive learning platform in order to engage students of diverse background in both online and face-to-face classes. Although the theory of adaptive learning approach has been widely discussed recently, there is no effective tool or course materials available to use directly in the bottleneck course of Data Structures and Algorithms, in which the DFW rate is much higher and the passing rate is much lower, especially when students have diverse background and various programming skills. Considering the dissimilar needs from students, we have redesigned this course using adaptive learning platform called Smart Sparrow, and created the weekly adaptive learning modules embedded into Blackboard LMS. The modules could be easily applied or modified for other computer science courses as well. Additional tools like Open Educational Resources and ZyBooks, as well as group-based assignments and projects are also utilized to further assist the students. Our goal is to evaluate the effectiveness of developed modules and student performance in this redesigned course. Preliminary results and assessment findings are discussed at the end of this paper.