Presented By O’Reilly and Cloudera
Make Data Work
September 11, 2018: Training & Tutorials
September 12–13, 2018: Keynotes & Sessions
New York, NY

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

Stephanie Fischer (datanizing GmbH)
11:00am–11:30am Tuesday, 09/11/2018
Data-driven business management
Location: 1E 10 Level: Beginner
Average rating: *****
(5.00, 1 rating)

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.

Photo of Stephanie Fischer

Stephanie Fischer

datanizing GmbH

Stephanie Fischer is the founder of datanizing GmbH. Stephanie has many years of consulting experience in big data, machine learning, and human-centric innovation. As a product owner, she develops services and products based on machine learning and content analytics. She is a frequent speaker at conferences and the author of articles on big data and machine learning.

Comments on this page are now closed.


Picture of Stephanie Fischer
Stephanie Fischer | FOUNDER & CEO
09/07/2018 5:16am EDT

Dear attendees, welcome to the talk!

I’m traveling from Munich to NYC and be sure, I’m coming well prepared. I’ve read 1.6 million posts in the "NYC Tripadvisor travel forum”: . I didn’t only read, I also made sense out of it. In this session, you’ll find out how I did it – and how you can, too!

Spoiler alert: Machine learning will play an important role.

What you can expect from the talk
If you would like to get to know a hands-on data-driven approach to deriving insights from text amounts – this talk is for you. I’ll explain the methods with a lot of examples. You can apply it to any kind of large text amounts.

Also, to all of you who are curious about which trending drinks you should be ordering in the evening – join the talk for more insights on this essential data-driven topic! ☺