Abstract:
|
There are now twice as many sensors (e.g., smartphones) in the Internet of Things and an equivalent number of social media accounts relative to the general population. The resultant explosive growth in data volume represents great opportunities for those who can find a signal in this vast collection of unstructured and uncertain noise. We show how to use text analytics (using R and SAS JMP) to efficiently search and analyze large volumes of open source material on innovative technologies, associated maturity levels, current applications and primary competitors. We scrape competitor websites, analyze patent databases, perform text mining on a collection of technical journal articles, and extract real-time information from social media (Twitter). The purpose is to identify critical themes of interest, associated documents or posts, and transform the unstructured data into usable variables through Singular Value Decomposition. Text analytics with data visualization, cluster analysis and decision tree capabilities provide a complement to traditional methods to characterize markets.
|