SpotFlow: Tracking Method Calls and States at Runtime
RapidMiner - Don’t Forget to Pack Text Analytics on Your Data Exploration Journey
1. RapidMiner - Don’t Forget to Pack Text
Analytics on Your Data Exploration Journey
February 2018
2. About Basis Technology
2
● Expertise: find meaning in unstructured text
○ NLP provider
● Product: Rosette (text analytics)
○ both on-premise and in the ‘cloud’
● Gil Irizarry - Director of Engineering
3. What will you learn?
3
● Where to find the Rosette operator
● How to use NLP operators within RapidMiner Studio
● What types of insights can we gain from text
4. How to apply what you’ll learn
4
● All the operators are
available in the
RapidMiner Marketplace.
● Free tier in the public
Rosette API allows 10K
calls per month
5. Sample Use Cases
5
● How engaged are fans of different TV shows?
● How is technology covered in the NY Times?
● Does having a location in an Airbnb title affect number of reviews?
● What are the most recurring names in foreign news?
Expertise: find meaning in unstructured text
Product: Rosette (text analytics)
NLP provider- area of computer science aimed at applying software to tackle problems in text analytics
Rosette is available both on-premise and in the ‘cloud’
Gil Irizarry is a Director of Engineering at Basis, managing teams working on name matching and identity resolution
Assess product engagement via sentiment analysis
Question: How engaged are fans of different TV shows?
Assess media coverage of particular topics
Question: How is technology covered in the NY Times?
Determine effectiveness of posts via entity extraction
Question: Does having a location in an Airbnb title affect number of reviews?
Translate and Deduplicate name list
Question: What are the most recurring names in foreign news?