An Interaction Embedded Framework for Healthcare Search

People without medical background usually seek health information from Web search engines using queries with the circumlocutory style, such as a description of observations, instead of professional symptoms or medical terms. However, the existing commercial search engines performs better on professional terms than the nonprofessional ones. Therefore, we propose an interaction-embedded framework for healthcare search to fit this gap. First, we absorb the MeSH and Wikipedia data as the knowledge resources to translate the circumlocutory queries into medical related terminologies. Then, we embed the user interaction into the search process to better capture users' intents. Finally, we perform a series of experiments on the TREC and CLEF eHealth collections for evaluation purpose. The experimental results show that our proposed framework are promising and outperforms the traditional retrieval algorithms.