Knowledge discovery from user health posts

Online health communities offer tremendous medical information that could be available to all. However as is the case with other data intensive applications, this information contains hidden patterns which if explored, analyzed and understood could be very useful for administrators, medical practitioner sand patients alike. There are websites where patients express their experiences or side-effects on drugs used. In this work we collect such real time health posts from reputed websites, and perform data mining to determine the various possible associations from these posts. Also, we shall perform knowledge discovery from user posts, whereby useful `patterns' about groups like: disease to disease, disease to drug and drug to symptom are discovered.