Encyclopedia of Educational Innovation

Living Edition
| Editors: Michael A. Peters, Richard Heraud

Adaptive Personalized eLearning

  • Reem Al-MahmoodEmail author
Living reference work entry
DOI: https://doi.org/10.1007/978-981-13-2262-4_164-1


Introduction: Adaptive Personalized eLearning

Interest in adaptive education arose in the 1970s beyond the one size fits all model of education to accommodate the diversity and needs of learners (Glaser 1977). With the advent of computers, digital technologies, the World Wide Web, and new digital platforms, adaptive digital education emerged through the pioneering work of Peter Brusilovsky and his colleagues on adaptive web-based systems in the mid-1990s (see Brusilovsky 1996; Brusilovsky et al. 1996, 1998). Developments in computerized adaptive testing (Wainer et al. 2000) furthered interest in adaptive digital education and intelligent tutoring systems. With the proliferation of digital learning and the emergence of adaptive elearning platforms and data-driven algorithmic education through data mining, learning analytics, and powerful machine learning, adaptive personalized elearning (APeL) is becoming more viable for every learner. APeL is emerging as a solution to higher education’s mission to maintain student engagement, increase success, and provide customized education at scale. Hence, there is rising interest in its affordances with various universities partnering on an institutional scale with adaptive elearning platform vendors to transform their digital education to be personalized, adaptive, and customized (Tyton Partners 2016). This entry outlines what APeL is and discusses its affordances, challenges, and implications for designing, teaching, and learning in the twenty-first century.

Personalized learning means that each learner’s needs and goals can be targeted with appropriate content and activities. This of course can be done face-to-face but only at small scale. Customized learning through adaptive pathways does this personalization dynamically in real time to produce specific learning pathways, recommendations, and feedback according to each learner’s needs, interests, input, and knowledge level. Personalization can vary from identifying names, roles, profiles, or tasks for each learner, varying the content level, tone, and voice accordingly to localizing content, for example. Using a user’s name or linking to results of an APeL module or assessments can help personalize the experience for each learner so it feels like it is tailor made for them.

Adaptive elearning can be done at scale as it is digital data-driven and responds to each learner’s input and performance and anticipates content, resources, and learning pathways. Here, the adaptive pathways adjust to users’ input to provide customized feedback and activities. A user can progress at their own pace, select and skip sections, choose beginner or advanced material, or retrace their steps. The adaptive platform with its pedagogical lesson design dynamically adjusts to a user’s advanced and novice levels and any corrections needed toward mastery. So the content pathways are personalized for each student – so already proficient learners can accelerate through and skip sections, while novice learners can be scaffolded with more support and introductory activities and sections. Essentially, the platform “learns” from and about each user and adapts to their needs.

Adaptive Personalized eLearning Affordances

An overview of APeL affordances is outlined for educators, designers, learners, and universities. The benefit of adaptive learning with its learning analytics is that it can provide sophisticated data-driven personalized enriched student learning experiences. Flexibility is at the heart of an adaptive platform in that content can be modularized and integrated into subjects and courses to supplement, complement, augment, or aid student learning across blended and online modalities. University contingencies will dictate degrees of adoption, support, and scale.

Personalized to Each Learner

The power of APeL platforms is that it offers individualized learning which is learner-centered and adaptive to each user’s learning needs. For example, APeL pathways can adapt to individual learners’ needs based on content input, interactivity, assessments, affective states, and learning style preferences; hence, information could be presented to suit students’ learning preferences (e.g., visual, audio, video, verbal, textual).

Engaging for Learners

APeL platform sophistication can afford designing engaging interactive content with vibrant and enticing aesthetics. Activities and lesson entry points can be designed to encourage user roles such as explorer, adventurer, gamer, or seeker, for example, or can be user goal-oriented. For example, in an APeL lesson, Digital Identity: Making Your Mark!, about e-reputation, social media, digital identity, and employability (Al-Mahmood et al. 2018), various learning design pathways are possible across and within the three modules: (1) Your Digital Identity, (2) Your Digital Impression, and (3) Your Digital Mark. The platform allows learning design configurations from sequential module completion to user choice according to needs. User activity questions and scenarios ranged from university students wanting to get their dream job to analyzing their social media use to reflecting on privacy and data permanency online, as exemplified in these sample activities:
  • Have you googled yourself lately?

  • Can social media really get you that dream job?

  • Can social media really get you fired?

  • Social media and entrepreneurship

  • What type of social media user are you?

Each user can be guided according to their individual responses and goals at each stage, and various pathways can be suggested by the platform as well as selected by the user. So, for example, in the above where users complete quizzes to identify what type of social media user they are (prolific, selective, curious, or indifferent), specific activity pathways can be suggested based on profile type and user analytics. For example, what should a curious profile outcome do to become a more prolific user and what advantages might there be in this could be one outcome option; or how can a prolific user be more strategic and targeted in improving their chances of getting that dream job can be another option and so on. The system basically responds to each user with outcomes and options rather than having a one size fits all design.

Ultimately, adaptive personalized designs can be evolved for any area from novice to mastery level, for example, in leadership, they can be based on leadership style profiles; or in medicine, they can be based on user types from emergency doctor, family physician, hospital ethicist, nurse manager, to patient advocate. The adaptive personalization design makes engagement more powerful for learners as content is pitched to accommodate their needs and requirements.

Empowering for Learners and Educators

Adaptive pathways allow each learner/user to choose how they want to navigate through an elearning lesson. An adaptive learning system can also guide learners and provide choice by adjusting to each user’s needs. This enables each learner’s background knowledge to be valued and respected (Educause 2017). Further, adaptive elearning pathways not only provide time, place, and pace (faster or slower) flexibility but also dynamic real-time feedback for each user, catering to learner profiles and their learning styles. Overall, such platforms can enable instructors and designers (and even students as co-creators/designers) to create vibrant, aesthetically pleasing, and engaging content that is pedagogically driven while facilitating experimentation and innovation.

Illuminating for Educators and Designers

APeL platforms can provide deeper insights for educators and designers. Significantly, the dynamic real-time analytics end can be viewed at any stage as educators can monitor each student and know who needs assistance, and get a sense of difficult concepts for students, as well as their students’ engagement with the curriculum, and hence they can facilitate intervention for at risk students to avoid failure and provide support (Educause 2017), as well as provide more sophisticated content for the high flyers. The viewing power can be leveraged both ways as students get to know more about themselves through feedback and the student-facing learning analytics of the adaptive platforms, and educators get to know more about their students’ learning through the back-end analytics. The platforms can facilitate comparisons across users, courses, and years, as well as amass cumulative user data for sophisticated analysis. Overall, access to such data informs evidence-based learning design.

Adaptable and Sustainable for Educators

A powerful feature of APeL platforms is that the content can be adapted, modularized, and modified in real time based on embedded learning analytics. So lessons can be modified and copied for various cohorts and can be shareable across instructors or even universities. Overall, delivering APeL can be done at scale to thousands of students. Further, APeL modules can be delivered as stand-alone or integrated into blended/online subjects to augment, supplement, or complement learning, or they can be used independently as a study aid. Another aspect of APeL modules is that they can be used not only within regular semester times or course times but at any time throughout the year.

Adaptive Personalized eLearning Challenges and Considerations

While the affordances of APeL have been highlighted, there are a number of challenges. Strategically, an institution will need to establish if it has the capacity to invest, build, and evaluate APeL adoption and at what scale, by exploring its fit for purpose as an appropriate solution for their problem and setting. This entry outlines some of the issues to consider.


APeL platforms use data mining, learning analytics, machine learning, and algorithmic education, usually black boxed. Data use and surveillance provoke ethical concerns and disclosure issues. How to make these transparent to all stakeholders across designers, educators, and students/users needs to be a priority for institutions. APeL platform algorithms are value-laden and generally unavailable to universities and only visible by the platform vendor. Additionally, significant ethical concerns arise depending on where students’ personal and performance data are hosted, internally on the institutional LMS system or externally on the vendor’s server, for example. Hence, ethics clearance is required, as well as understanding of privacy agreements and consideration of local and global data policies and privacy laws. Further complications are that APeL digital vendors and educational institutions can be under different jurisprudence systems because of their geographical locations across countries.


While Educause (2017, p. 2) suggests that adaptive learning “enables the delivery of personalized learning at scale contributing to greater levels of academic success for more students in a cost-efficient manner”, this will depend on an institution’s fiscal situation as well as deployment scale. Existing and emerging adaptive elearning platforms vary in design and licensing costs and agreements. Generally, the greater the number of users, the lower the licensing costs. Generally, institutional annual licensing cost options can provide better returns on investment for unlimited users compared to small-scale adoptions. Additionally, maintenance, hosting, upgrade, and (re)design costs have to be considered for sustainability. All these need to be negotiated between the institution and the platform vendor on a case-by-case basis. An institution also needs to consider time release for its staff to liaise and develop adaptive personalized modules/lessons/courses and consider sustainability and capacity building. Further, with the expansion of the APeL vendor space and opportunities for open-source platforms emerging, evaluating open versus vendor platforms will be vital for any institution. The return on investment will need to be considered carefully.


Sufficient time allocation is needed to develop high-quality adaptive personalized content and undertake curriculum content mapping. This is underestimated compared to standard LMS (learning management systems) subject development because multiple user pathways need to be mapped as well as personalized assessment responses. Further, designing and delivering adaptive courseware require a multidisciplinary team approach at an institutional level as well as the vendor level. So factoring in time for staff availability and development is crucial. Seemingly short lessons of 1 hour could take up to 6 months to a year to develop and pilot and refine, depending on the level of complexity and sophistication of adaptive pathways.

Staff Capacity Building

When introducing a new technology platform tool, especially an APeL one, the pedagogical transformation required also needs to be addressed, in addition to the tool’s capabilities. How such support is built and sustained are important considerations. Establishing sustainability of training and upskilling learning designers, educational developers and educators needs to be considered. The adaptive platform vendor often includes training resources and often a number of free online training sessions. These are questions to consider when selecting a platform.

Adaptive Personalized eLearning Platform Sophistication and Maturity

When exploring APeL platforms, some features to consider are the platform’s usability and intuitive features, ease of use versus complexity, ease of navigating, aesthetics, interactive options, degrees of authoring and configuration at local/external levels, user and administrative permissions, learning analytics and dashboards, as well as the way the adaptivity is powered (how it works), i.e., a rule-based and algorithm-driven system, which recommends different pathways for a learner and the mastery level for students to aspire toward. Having a technical understanding of some of these differences can assist in understanding the sophistication of the adaptivity and personalization aspects of the platform. There are indeed challenges in the adaptive technologies and pedagogical assumptions and models adopted. Overall, enriched sophistication and use and integration with multiple learning technologies within and beyond an institution are a paramount requirement.

Also, important considerations are the authoring platform and its usability aspects and how to create adaptive learning pathways. (These can also be mapped in hard copy in the first instance visually on large sheets of paper using colored Post It notes).

Further, how the lesson or module can be captured for longevity and active learning by the user (e.g., some platforms provide digital notetaking and screen capture options that can be emailed to a user’s email account) are vital.

Topic Suitability and Modeling

Content needs to be evolved to suit diverse learners’ requirements to address personalization and meaningful learning experiences; hence, “appropriate modelling of the learners’ needs and preferences”, “representation of pedagogical strategies”, and “representation of learning design” are necessary (Turker et al. 2006) and can be complex and challenging. Commonly, APeL platforms have been used with topics that involve factual or procedural knowledge and competency-based areas. However, reflective and more open-ended topics are also possible (Al-Mahmood et al. 2018).

Inclusivity, Diversity, Accessibility, and Universal Design

In developing any APeL lessons, design needs to be inclusive and accommodating of diverse learners. Hence, ensuring accessibility is essential and needs to be budgeted into the design process according to universal inclusivity and accessibility design principles. For example, how will drag and drop activities be transformed for a user who is blind, or who will pay for audio and video transcripts or closed captions, and are there multiple input mechanisms are important aspects, along with compliance with universal design principles.

Intellectual Property, Copyright, and Commercialization

It is important to determine copyright ownership and intellectual property of the content and design of APeL lessons with the vendor and university users and required sharing permission contracts. This becomes even more complicated when institutions may work on designing and sharing APeL modules locally or globally. Hence, it becomes necessary to engage with universities’ legal and copyright offices and to consider protocols for sharing. Clearly articulated ownership and commercialization statements and open education options are discussions that must be had early and updated annually.

Overall, these are some of the current issues and challenges, and with the more global APeL platform vendors and open-source competitors emerging, further considerations will arise.

Conclusion: Implications of Adaptive Personalized eLearning for Pedagogy and Universities

Having summarized the affordances and challenges of APeL, it will be important to stay abreast of the emerging evidence-based academic outcomes of this newly emergent field. With more competitive APeL platform vendors emerging and existing traditional LMS platform vendors evolving and adding adaptive capacity, it would be judicious to compare any open-source developments in any adoption trial plans. What seems certain for now is that interest in APeL is growing among universities and corporate organizations. What is also certain is that there can be significant benefits in developing high-quality rich and engaging APeL lessons given that there are significant benefits to student learning given that these platforms afford formative evaluation, effective feedback, mastery-based learning, and interactive content (Hattie 2009). These all sit well within the affordances provided by developing high-quality interactive adaptive personalized learning solutions.

By using APeL, a paradigm shift from teacher-centered to learner-centered focus facilitates learner choice where the learner controls the pace, content, and activities, as teachers become facilitators, guides, and mentors through the learning experience. Not only can this process empower learners, but it empowers educators by having dynamic analytics to learn about their students and facilitate learning. Ultimately, experimenting with innovation is the aim to provide engaging, insightful, and customized rich learning experiences for every student. Providing tailored learning through adaptivity can lead to more engaging and rewarding experiences for learners. Overall, developing such APeL solutions can provide powerful returns on investment for an institution towards better teaching and learning success for all.


  1. Al-Mahmood, R., Corbin, J., Balavijendran, L., & Ondracek, C. (2018). Digital identity and e-reputation: Showcasing an adaptive eLearning module to develop students’ digital literacies. In M. Campbell, J. Willems, C. Adachi, D. Blake, I. Doherty, S. Krishnan, S. Macfarlane, L. Ngo, M. O’Donnell, S. Palmer, L. Riddell, I. Story, H. Suri, & J. Tai (Eds.), Open Oceans: Learning without Borders. Proceedings ASCILITE 2018 (pp. 25–34). Geelong. http://ascilite.org/wp-content/uploads/2018/12/ASCILITE-2018-Proceedings.pdf.
  2. Brusilovsky, P. (1996). Methods and techniques of adaptive hypermedia. User Modeling and User-Adapted Interaction, 6(2–3), 87–129.CrossRefGoogle Scholar
  3. Brusilovsky, P., Schwarz, E., & Weber, G. (1996). ELM-ART: An intelligent tutoring system on World Wide Web. In C. Frasson, G. Gauthier, & A. Lesgold (Eds.), Third international conference on Intelligent Tutoring Systems, ITS-96 (Vol. 1086, pp. 261–269). Berlin: Springer. http://www.contrib.andrew.cmu.edu/~plb/ITS96.html.CrossRefGoogle Scholar
  4. Brusilovsky, P., Eklund, J., & Schwarz, E. (1998). Web-based education for all: A tool for development adaptive courseware. Computer Networks and ISDN Systems, 30(1–7), 291–300.CrossRefGoogle Scholar
  5. Educause. (2017). 7 Things you should know about adaptive elearning. https://library.educause.edu/resources/2017/1/7-things-you-should-know-about-adaptive-learning
  6. Glaser, R. (1977). Adaptive education: Individual diversity and learning. New York: Holt, Rinehart and Winston.Google Scholar
  7. Hattie, J. (2009). Visible learning: A synthesis of over 800 meta-analyses related to achievement. New York: Routledge.Google Scholar
  8. Turker, A., Görgün, İ., & Conlan, O. (2006). The challenge of content creation to facilitate personalized e-learning experiences. International Journal on E-Learning, 5(1), 11–17.Google Scholar
  9. Tyton Partners. (2016). Learning to adapt 2.0: The evolution of adaptive learning in higher education. http://tytonpartners.com/library/learning-to-adapt-2-0-the-evolution-of-adaptive-learning-in-higher-education/
  10. Wainer, H., Dorans, N. J., Flaugher, R., Green, B. F., & Mislevy, R. J. (2000). Computerized adaptive testing: A primer. New York: Routledge.CrossRefGoogle Scholar

Copyright information

© Crown 2019

Authors and Affiliations

  1. 1.La Trobe UniversityMelbourneAustralia

Section editors and affiliations

  • David Parsons
    • 1
  1. 1.The Mind LabAucklandNew Zealand