What is it about?
Readability is the ease with which a reader can understand a text. In this work, we explore methods to assess the readability of health content automatically. We produced enriched vocabularies of simple and difficult words with several metrics related to health word difficulty. We then proposed and computed health-specific features based on information from the enriched vocabularies. Then, we compared different learning algorithms using the proposed features and different sets of features using the same model. To evaluate our methods, we built and used a dataset composed of Simple English Wikipedia articles and the respective documents in ordinary Wikipedia.
Featured Image
Photo by Brian McGowan on Unsplash
Read the Original
This page is a summary of: Proposal and Comparison of Health Specific Features for the Automatic Assessment of Readability, July 2020, ACM (Association for Computing Machinery),
DOI: 10.1145/3397271.3401187.
You can read the full text:
Contributors
The following have contributed to this page
