Recent advances in adaptive learning sciences (such as machine learning, natural language processing, and Bayesian knowledge tracing) are transforming a designer's ability to personalize instruction.
For this reason a new chapter was added to the second edition of The Handbook on Learning and Instruction discussing the current state of the science and how practitioners can apply it effectively .
As a co-author of this chapter, I explored two questions from a designer's perspective:
Adapting to Learners
Learners differ in a great many ways (knowledge state, interest, goals, affective state, strategic behaviors, learning styles, etc.), so which learner charactaristics should we adapt to?Adapting Effectively
Adaptations can happen in several time-frames (per action, per problem, per course, etc.), so which loops are effective at adapting to available data?Recent advances in adaptive learning sciences (such as machine learning, natural language processing, and Bayesian knowledge tracing) are transforming a designer's ability to personalize instruction.
For this reason a new chapter was added to the second edition of The Handbook on Learning and Instruction discussing the current state of the science and how practitioners can apply it effectively .
As a co-author of this chapter, I explored two questions from a designer's perspective:
Adapting to Learners
Learners differ in a great many ways (knowledge state, interest, goals, affective state, strategic behaviors, learning styles, etc.), so which learner charactaristics should we adapt to?Adapting Effectively
Adaptations can happen in several time-frames (per action, per problem, per course, etc.), so which loops are effective at adapting to available data?