Using the probability of readability to order Swedish texts

In this study we present a new approach to rank readability in Swedish texts based on lexical, morpho-syntactic and syntactic analysis of text as well as machine learning. The basic premise and theory is presented as well as a small experiment testing the feasibility, but not actual performance, of the approach. The experiment shows that it is possible to implement a system based on the approach, however, the actual performance of such a system has not been evaluated as the necessary resources for such an evaluation does not yet exist for Swedish. The experiment also shows that a classifier based on the aforementioned linguistic analysis, on our limited test set, outperforms classifiers based on established metrics used to assess readability such as LIX, OVIX and Nominal Ratio.