From chaos to insight: Automatically derive value from your user-generated content

Whether customer emails, product reviews, company wikis, or support communities, user-generated content (UGC) as a form of unstructured text is everywhere, and its growing exponentially. Stephanie Fischer explains how to discover meaningful insights from the UGC of a famous New York discussion forum.

Whether customer emails, product reviews, company wikis, or support communities, user-generated content (UGC) as a form of unstructured text is everywhere, and it’s growing exponentially—driving interest in automated evaluation (aka a “treasure hunt”). Similar techniques have been successfully used for structured information (data warehouses) for quite a while. However, in contrast to structured data from things like sensors, unstructured data requires more preprocessing in order to turn it into a source for trend monitoring, ideas to innovate, and much more. Stephanie Fischer explains how to discover meaningful insights from the UGC of a famous New York discussion forum. She demonstrates how to use machine learning to find the most exciting topics, follow emerging trends, and identify outliers and use beautiful network graphs to show which dynamics arise when users interact with each other. Combined with other interactive dashboard widgets, this allows visual exploration of the UGC.