Predicting the Comprehension of Health Web Documents Using Characteristics of Documents and Users

The Web is frequently used as a way to access health information. In the health domain, the terminology can be very specific, frequently assuming a medico-scientific character. This can be a barrier to users who may be unable to understand the retrieved documents. Therefore, it would be useful to automatically assess how well a certain document will be understood by a certain user. In the present work, we analyse whether it is possible to predict the comprehension of documents using document features together with user features, and how well this can be achieved. We use an existing dataset, composed by health documents on the Web and their assessment in terms of comprehension by users, to build two multivariate prediction models for comprehension. Our best model showed very good results, with 96.51% accuracy. Our findings suggest features that can be considered by search engines to estimate comprehension. We found that user characteristics related to web and health search habits, such as the success of the users with Web search and the frequency of the users' health search, are some of the most influential user variables. The promising results obtained with this dataset with manual comprehension assessment will lead us to explore the automatic assessment of document and user characteristics.