Combining Readability Formulas and Machine Learning for Reader-oriented Evaluation of Online Health Resources
Yanmeng Liu, Meng Ji, Shannon Lin, Mengdan Zhao, Ziqing Lyv
Abstract
Websites are rich resources for the public to access health information, and readability ensures whether the information can be comprehended. Apart from the linguistic features originated in traditional readability formulas, the reading ability of an individual is also influenced by other factors such as age, morbidities, cultural and linguistic background. This paper presents a reader-oriented readability assessment by combining readability formula scores with machine learning techniques, while considering reader background. Machine learning algorithms are trained by a dataset of 7 readability formula scores for 160 health articles in official health websites. Results show that the proposed assessment tool can provide a reader-oriented assessment to be more effective in proxy the health information readability. The key significance of the study includes its reader centeredness, which incorporates the diverse backgrounds of readers, and its clarification of the relative effectiveness and compatibility of different medical readability tools via machine learning.