Machine Intelligence for Health Information: Capturing Concepts & Trends in Social Media via Query Expansion
X Su, Hanna Suominen and Leif Hanlen
In: Health Informatics Conference 2011 (HIC 2011),, August 2011, Brisbane Australia.
We aim to make health-related information retrieval from Twitter tweets faster and more precise. Background. The popularity of social media and micro-blogs has emphasized their potential for knowledge discovery and trend building. However, capturing and relating concepts in these short-spoken and lexically extensive sources of information requires search engines with increasing intelligence. Methods. Our approach uses query expansion techniques to associate query terms with the most similar Twitter terms to capture trends in the gamut of information. Results. Our method remains stable with an increasing number of tweets; this is crucial as large data sets are needed for capturing trends with high confidence. In addition, by considering two search tasks and two independent annotators, we have demonstrated the value, defined as improved efficacy and precision, of our search engine. These results encourage us to continue developing the search engine for discovering trends in health information available at Twitter.