Features indicating readability in Swedish text

Abstract

Studies have shown that modern methods of readability assessment, using automated linguistic analysis and machine learning (ML), is a viable road forward for readability classification and ranking. In this paper we present a study of different levels of analysis and a large number of features and how they affect an ML-system’s accuracy when it comes to readability assessment. We test a large number of features proposed for different languages (mainly English) and evaluate their usefulness for readability assessment for Swedish as well as comparing their performance to that of established metrics. We find that the best performing features are language models based on part-of-speech and dependency type.