Context Aware Personalized Learning for Deep Content Analysis: Adapting to Diverse Learning Environment for Truly Personalized Learning Experience

Personalized Learning delivers Learner with content and a dedicated Learning path by adapting to Learner preferences, needs, desires and interest thus by providing user LearnerCentred and Effective Educational Experience. Integrating Deep Content Analysis is the major issue in Personalized Learning as they rely on Learner profiling such as user preference, previous performance and Basic Demographic Information and they fail to provide true personalized Learning Experience. In order to provide Deep content Analysis Context Aware Personalized Learning (CAPL) takes the contextual factors such as Emotional state, time, location and environmental conditions. By considering these factors CAPL improves Learner's ability to absorb, apply and retain Knowledge. Various Algorithms such as Random Forest, Logistic regression, SVM are used for classifications, VADER (Valance aware Dictionary sEntiment Reasoner) for emotion identification and TF-IDF (Term Frequency-Inverse Document Frequency) for text feature Extraction are used in CAPL. The Main Objective of this research is to better respond to the unique needs of the individual Learner in real time thus providing more realistic Personalized Learning. In this paper context based Personalized learning and the methods used to achieve CAPL are discussed.