A Machine Learning-Based Readability Model for Gujarati Texts

This study aims to develop a machine learning-based model to predict the readability of Gujarati texts. The dataset was 50 prose passages from Gujarati literature. Fourteen lexical and syntactic readability text features were extracted from the dataset using a machine learning algorithm of the unigram parts of speech tagger and three Python programming scripts. Two samples of native Gujarati speaking secondary and higher education students rated the Gujarati texts for readability judgment on a 10-point scale of "easy" to "difficult" with the interrater agreement. After dimensionality reduction, seven text features as the independent variables and the mean readability rating as the dependent variable were used to train the readability model. As the students' level of education and gender were related to their readability rating, four readability models for school students, university students, male students, and female students were trained with a backward stepwise multiple linear regression algorithm of supervised machine learning. The trained model is comparable across the raters' groups. The best model is the university students' readability rating model. The model is cross-validated. It explains 91% and 88% of the variance in readability ratings at training and cross-validation, respectively, and its effect size and power are large and high.