Domain specific document retrieval framework for real-time social health data

Abstract

With the advent of the web search and microblogging, the percentage of Online Health Information Seekers (OHIS) using these online services to share and seek health real-time information has increased exponentially. OHIS use web search engines or microblogging search services to seek out latest, relevant as well as reliable health information. When OHIS turn to microblogging search services to search real-time content, trends and breaking news, etc. the search results are not promising. Two major challenges exist in the current microblogging search engines are keyword based techniques and results do not contain real-time information. To address these challenges, we developed an approach to search near real-time and reliable content from Twitter, based on triple-pattern mining, near real-time retrieval, and ranking considering popularity and relevancy of the results.