The Training Place home

Adaptive and
Personalized Learning

Individual Learning Differences

Personalization Framework | Mass Customized Learning
Personalization Research


"Technologically, researchers are making progress in realizing the personalized learning dream. The missing link is the instructional design perspective that understands the impact of emotions and intentions and embraces a truly personal understanding of how individuals want, or intend, to learn differently."

As designers, we can collect and analyze information about how individuals learn in a given situation and more effectively provide personalized solutions.

Collecting critical success attributes common to the learning group is vital in helping learners improve learning ability, understand how they learn best, and make educated choices about managing their learning environments.

Personalization includes using learner-specific strategies that may take many forms as it adapts environments and offers alternative choices, including sequencing or presentation of content, practice, feedback, and assessment. Good instructors have been offering these personalization strategies in classrooms for years. In online learning situations, technology should ensure that these same strategies can be applied and increasingly self-managed by the online learners over time.

Basing instructional analysis, interpretations, and decisions on a standardized multidimensional framework developed by identifying critical success attributes helps to formalize the personalization process. Once organized for the targeted audience, the framework can be used to create a Blueprint for more Personalized Learning.

The Blueprint for Personalized Learning should use well-developed criteria based on iterative cycles of measurement to track each learner's interaction with the personalized solution. Results should measurably show how the learning solution becomes more valuable to the learner. The desired result should show an increased loyalty and affinity for the online learning solution over others.

However challenging, the transition to these new learning paradigms can be very rewarding for all.

New Book!!!! Reshaping Learning: Frontiers of Learning Technology in a Global Context, 2013, Series: New Frontiers of Educational Research, Huang, Ronghuai; Kinshuk; Spector, J. Michael (Eds.)

See: Chapter 6: Adapting for a Personalized Experience, Margaret Martinez

Personalization uses learner-specific strategies to address individual needs and expectations to support and promote individual learning success.

The Goal for Personalized Learning: Two individuals accessing the same personalized instruction simultaneously may see different presentations and progress and improve differently-- usually with greater satisfaction.

What is Personalized Learning?
(click here to view an article appearing
in the E-Learning Developers' Journal)

What is Mass Customized Learning?

        Personalization Framework

There are many ways to personalize learning. Using a well-tested Personalization Framework helps ensure that solutions and interpretations are consistent, relevant, and useful with measurable improvements. The Personalization Framework described here has four levels or perspectives. The fourth level has five major dimensions. From the simplest to the most complex, the dimensions for the are: 1) name recognition; 2) self-managed; 3) segmented; 4) cognitive-based; and (5) whole-person-based. Each dimension has a specific purpose and resulting impact. Your targeted goals and outcomes should govern your choice of these dimensions. These dimensions can work separately or in tandem to enhance the personalized learning experience.
  • Name Recognition Personalization
    Name recognition personalization is useful because most people value being acknowledged as an individual. As an example, the learner’s name appears at the top of the screen or previous accomplishments are marked.
  • Self-Managed Personalization
    Self-managed personalization enables learners (using questionnaires, surveys, registration forms, and comments) to describe preferences and common attributes. As an example, learners may take a pre-course quiz to identify existing skills, learning preferences, or past experiences.  Afterwards, solutions appear based on the learner-provided answers.
  • Segmented Personalization
    Segmented personalization uses demographics, geographics, psychographics, or other information to divide or segment learning populations into smaller, identifiable and manageable groups for personalization. As an example, learners that share a common job title or work in a certain department would receive content based on prescriptive rules that would support the learning and performance requirements for that specific segmented group.
  • Cognitive-Based Personalization
    Cognitive-based personalization uses information about learning preferences or styles from a primarily cognitive perspective to deliver content specifically targeted to differing learner attributes. As an example, learners may choose to use an audio option because they prefer hearing text rather than reading it. Or, a learner may prefer the presentation of content in a linear fashion, rather than a random presentation with hyperlinks. This type of personalization operates on more complex algorithms than the other types and is able to factor more learner attributes into each interaction. This type of personalization generally works by collecting data, monitoring learning activity, comparing that activity with other learner behavior, and predicting what the user would like to do or see next.
  • Whole-Person Personalization
    Whole-person personalization seeks to understand the deep-seated psychological sources (more than the conventional cognitive-based prescriptions) impacting differences in learning behavior, make predictions about delivering content, and deliver content specifically to help the learner achieve learning objectives and more importantly, improve learning ability and enhance online learning relationships. As the individual learns, the system also learns as it collects data, tracks progress, and compares responses and common patterns to improve responses, i.e., it becomes more precise over time. In its most sophisticated form, whole-person personalization requires real-time personalization to modify responses to a learner based on a changing perception throughout the learning experiences, as it occurs (like an instructor in the box).

Home | Mass Customized Learning | Page Top

Some projects were funded in part by the Society for Technical Communication
(STC Research Award, 1997-1998).
Updated October 2013 by Margaret Martinez & The Training Place, Inc.
E-mail comments to
Copyright © Margaret Martinez 1996-2013