Advances in Readability Research: A New Readability Web App for English

Abstract

Readability research and the entailing derivation of theoretically valid and high-performing readability assessment models are important components of reading education. There have been notable advances in the research of readability assessment following the advances of natural language processing techniques. Specifically, newer formulas make use of complex linguistic features that were previously unavailable, as well as contextually representative word-embeddings derived by training neural networks. However, there remain limitations for newer readability formulas, especially with respect to the employment of newer formulas by educational content creators. This paper provides an overview of readability research and introduces a new web app to help facilitate the application of state-of-the-art readability formulas for educational content creators and researchers through both an online interface and a separate API. An increase in accessibility and exposure for state-of-the-art readability formulas will assist in addressing many limitations of integrating readability research into educational technologies.