Cognitive Profiling in Life-Long Learning

Cognitive Profiling in Life-Long Learning

Taiyu Lin (Massey University, New Zealand), Kinshuk (Massey University, New Zealand) and Kinshuk (Massey University, New Zealand)
Copyright: © 2009 |Pages: 11
DOI: 10.4018/978-1-60566-198-8.ch043
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Statistics indicate that the information stored in the world doubles every 2.8 years (Keegan, 2000). The problem every country faces now is not how to create more information, but how to locate and utilise the available information. This amazing phenomenon brings on the dawn of a so-called knowledge economy within which market transactions are facilitated or even driven by knowledge that is acquiring more of the properties of a commodity (Houghton & Sheehan, 2000). Corporations like General Electric (GE) spend $500 million on training and education every year, and overall $62.5 billion was budgeted for formal training by U.S. organisations in 1999 alone (Keegan, 2000). Corporations and individuals are more and more required to absorb and keep updated the new information through on-the-job or private training in order to stay competitive. Thus, lifelong learning has become a common practice for a wide range of careers ranging from engineers to sales representatives and doctors to farmers. Technology-based instruction, within which electronic learning, e-learning, is the largest component, was predicted to have 60 to 75% of share attributed to the corporate training market in 2004 (Keegan, 2000). One of the main advantages of e-learning over traditional instructor-led training is its ability to provide individualisation and adaptivity to suit the learner’s need. Adaptive learning systems can adapt the learning content and presentation according to the characteristics of the learners (Beaumont, 1994; Costa, et al., 1991; Jonassen & Wang, 1990), and they aim at providing individualised courses similar to having the one-to-one privilege from a private tutor.
Chapter Preview
Top

Performance-Based Student Model

Two major types of performance-based models have been used in existing systems: state models and process models. In state models, a learner’s domain competence, which is identified as the most important feature in the existing systems, has to be constantly updated to reflect the progress in the student’s understanding. This is often accomplished by recording the nodes or concepts visited by the students and the result of the learning from some form of assessment. For example, the state model in CIRCSIM-Tutor is used to guide the planning of the tutoring dialogue, switch the tutoring protocols, and, in large, adjust the curriculum (Zhou & Evens, 1999).

Key Terms in this Chapter

Cognitive Trait Model: A model representing one or more cognitive traits of learners.

Student Model: A profile of a learner including a chosen set of attributes or characteristics related to the learning process.

Manifest: A defined student behaviour pattern or attribute, observable during the student’s learning process.

Performance-Based Models: Student models that profile the learners according to their performance.

Working Memory: Denotes the memory capable of transient preservation of information, which is functionally different from the memory that stores historical information (long-term memory).

Cognitive Traits: The abilities humans possess for cognition. Working memory is an example.

Individualised Temperament Network: A neural-network-like structure representing a particular cognitive trait (e.g., working-memory capacity) of the learner.

Complete Chapter List

Search this Book:
Reset