English as a Second Language (ESL) teachers often have difficulty matching the complexity of fiction texts with students' reading levels. Texts that seem appropriate for students of a given level can turn out to be too difficult. Furthermore, it is difficult to choose a series of texts that represent a smooth gradation of text difficulty. This paper attempts to address both problems by providing a complexity ranking of a corpus of 200 fiction texts written for adults (n=100) and children (n = 100). Computational linguistics and machine learning are used to create a classifier which is able to classify the corpus with an accuracy of 89%. The classifier is then used to provide a linear complexity rank for each text. An ESL teacher can select from the ranking 1) a beginning text that is aligned to a student's reading level and 2) a sequence of texts that are instantiate a gradual increase in complexity. The fine gradation in complexity minimizes the risk of presenting the student with text with a frustrating level of difficulty.
Leave a reply: