Social Media and Open Data Integration through SAS ® Visual Analytics and SAS ® Text Analytics for Public Health Surveillance
Manuel Figallo-Monge · 2015
A leading killer in the United States is smoking and, moreover, over 8.6 million Americans live with a serious illness caused by smoking or second-hand smoking. Despite this, over 46.6 million U.S. adults smoke cigarettes, cigars, and pipes all of which have been linked to chronic diseases. What about e-cigarettes – how might they affect this public health situation, particularly among each of the 50 United States? In other words, can monitoring public opinions of e-cigarettes using open data (such as Twitter), SAS ® Visual Analytics, and SAS ® Text Analytics help inform insights on the potential dangers of these new products? To what extent can social media provide lead generation for anti-smoking campaigns, prioritization of surveys, and early detection of e-cigarette outcomes? These are some of many analytic questions which may arise in coming years, as more data pertaining to e-cigarettes becomes available. As such, this paper will not attempt to make any conclusive decisions on the potential role e-cigarettes may play in chronic health conditions. Rather, we will aim to provide a broad overview of a technological solution that can be utilized for the purpose of public health surveillance. In short, this paper will introduce the topics of open data, APIs, SAS ® Intelligence Platform (especially, SAS ® Metadata, stored processes, macros) as well as SAS ® capabilities including text and statistical analysis and visualizations.