Text Mining for Personal Health Information on Twitter

摘要

Internet and online social networks have profoundly changed the way the general public can express their opinions on a multitude of topics. With 19%-28% of Internet users participating in online health discussions, it became imperative to incorporate online-posted information into decisions related to public health. In order to make educated decisions, there is a necessity to develop methods that efficiently and effectively extract personal health information from the online messages. In this work we introduce two semantic-based methods for mining personal health information in Twitter. One method uses WordNet as a source of health-related knowledge, another an ontology of personal relations. We compare their performance with a lexicon-based method that uses an ontology of health-related terms. Empirical results show that in