PROJECT TITLE:

Network-Based Modeling and Intelligent Data Mining of Social Media for Improving Care - 2015

ABSTRACT:

Intelligently extracting data from social media has recently attracted great interest from the Biomedical and Health Informatics community to simultaneously improve healthcare outcomes and scale back prices using shopper-generated opinion. We propose a two-step analysis framework that focuses on positive and negative sentiment, similarly because the side effects of treatment, in users' forum posts, and identifies user communities (modules) and influential users for the purpose of ascertaining user opinion of cancer treatment. We tend to used a self-organizing map to analyze word frequency information derived from users' forum posts. We have a tendency to then introduced a completely unique network-based approach for modeling users' forum interactions and utilized a network partitioning methodology primarily based on optimizing a stability quality live. This allowed us to determine consumer opinion and determine influential users at intervals the retrieved modules using info derived from both word-frequency information and network-based mostly properties. Our approach can expand analysis into intelligently mining social media data for shopper opinion of varied treatments to supply rapid, up-to-date info for the pharmaceutical business, hospitals, and medical workers, on the effectiveness (or ineffectiveness) of future treatments.