Assessing English language sentences readability using machine learning models

Abstract

Readability is an active field of research in the late nineteenth century and vigorously persuaded to date. The recent boom in data-driven machine learning has created aviable path forward for readability classification and ranking. The evaluation oftext readability is a time-honoured issue with even more relevance in today’sinformation-rich world. This paper addresses the task of readability assessment forthe English language. Given the input sentences, the objective is to predict its level ofreadability, which corresponds to the level of literacy anticipated from the targetreaders. This readability aspect plays a crucial role in drafting and comprehendingprocesses of English language learning. Selecting and presenting a suitable collectionof sentences for English Language Learners may play a vital role in enhancingtheir learning curve. In this research, we have used 30,000 English sentences forexperimentation. Additionally, they have been annotated into seven differentreadability levels using Flesch Kincaid. Later, various experiments were conductedusing five Machine Learning algorithms, i.e., KNN, SVM, LR, NB, and ANN.The classification models render excellent and stable results. The ANN modelobtained an F-score of 0.95% on the test set. The developed model may be used ineducation setup for tasks such as language learning, assessing the reading and writingabilities of a learner