Feature-based Assessment of Text Readability

Accurately-predicting the readability of text documentation is important for educators, writers and learners. In perspective of linguistics, many researchers study text readability by analyzing semantics, vocabulary, syntax, expression, stylish, and cultural. The considerations of these facts are combined together to generate a common text readability predictor. In this paper, we first review the status field with conventional methods being used to assess and evaluate text readability. Our emphasis is on text feature selection, since the features commonly effects the understanding of text content. The text features for L2 (second language) readers are utilized for the present analysis using Coh-Metrix. We found that the effects of text features to L2 learners are different to native language readers.