Multi-pedia: Ranking and clustering of text based on difficulty

In this model, we attack the common problem of varying comprehending and perception capacities which differ with every individual. For understanding any concept, different individuals might require different levels of difficulty. Thus, we propose a model that performs clustering of text based on difficulty. Initially, with different feature extraction techniques, the scores of various textual characteristics for every explanation are evaluated. The database of explanations is then segregated according to the different topics. Lastly, these explanations are ranked using clustering techniques which involve the use of standard classifiers: - K-Means and Hierarchical Agglomerative Clustering.