About the Author:
Dr Alvin Chan is the Yvon Pfeifer Professor of Artificial Intelligence & Emerging
Technologies at Cambridge Corporate University (Switzerland), specialising in AI
and educational innovation. He has led teacher training in digital pedagogy and
generative AI, developed AI-powered educational applications, and pioneered the
integration of Multiple Intelligence frameworks. Dr Chan has held academic
leadership roles, serves on editorial boards, and is a peer reviewer for leading journals
in artificial intelligence. His work centres on scalable, inclusive AI solutions for
teaching and learning.
Abstract
Learner profiling is a cornerstone of personalised education, enabling tailored
instructional strategies that address individual learner differences. However, many
profiling tools focus narrowly on a single dimension, such as behavioural tendencies
or learning styles, limiting their comprehensiveness and accuracy. The Learner’s Plus
Profiling Suite (LPPS) innovatively integrates four complementary surveys—
ActionMap (behavioural style), LearnMap (learning style), TeachMap (teaching
preference), and SmartsMap (multiple intelligences)—to triangulate data and generate
a holistic, multi-dimensional learner profile. This paper presents an in-depth
theoretical analysis of each survey’s foundation, synthesises empirical evidence on
their individual and combined benefits, and critically examines the enhanced accuracy
and professional recommendations enabled by data triangulation. Drawing on
extensive literature, case studies, and policy frameworks, the paper argues that LPPS
offers superior insights into learner needs, engagement, and potential, making it an
indispensable tool for educators and a compelling case for universal parental consent.
The paper concludes with implications for educational practice, ethical considerations,
and future research directions.
Keywords: Learner Profiling, Personalised Education, Behavioural Style, Learning
Style, Multiple Intelligences, Data Triangulation.