A Personalised Approach to Adaptive Tutoring using Machine Learning and Natural Language Processing

Abstract

The Adaptive Learning Application (ALA) is an intelligent tutoring system that identifies the manner in which a student assimilates information, and accordingly evolves itself to generate personalised lesson plans that optimise learning. The ALA is built using a combination of a Weighted Support Vector Machine, a custom-built algorithm amalgamating versions of the FP-Growth and Genetic algorithms, and Natural Language Processing techniques. Thus, it uses both supervised and unsupervised learning to learn two things in parallel – how to quantifiably identify the types of topics a student finds difficult, and the best way in which to teach a topic of a particular difficulty level. Natural Language Processing techniques including but not limited to POS-tagging and TF-IDF scores are used to evaluate how much the student has learnt. The results are propagated back into a feedback loop to facilitate learning.