Language complexity in on-line health information retrieval

Abstract

The number of people searching for on-line health information has been steadily growing over the years so it is crucial to understand their specific requirements in order to help them finding easily and quickly the specific information they are looking for. Although generic search engines are typically used by health information seekers as the starting point for searching information, they have been shown to be limited and unsatisfactory because they make generic searches, often overloading the user with the provided amount of results. Moreover, they are not able to provide specific information to different types of users. At the same time, specific search engines mostly work on medical literature and provide extracts from medical journals that are mainly useful for medical researchers and experts but not for non-experts. A question then arises: Is it possible to facilitate the search of on-line health/medical information based on specific user requirements? In this paper, after analysing the main characteristics and requirements of on-line health seeking, we provide a first answer to this question by exploiting the Web structured data for the health domain and presenting a system that allows different types of users, i.e., non-medical experts and medical experts, to retrieve Web pages with language complexity levels suitable to their expertise. Furthermore, we apply our methodology to the results of a generic search engine, such as Google, in order to re-rank them and provide different users with the proper health/medical Web pages in terms of language complexity.