|
Activity Number:
|
22
- The World of Data Analysis Professionals
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, July 29, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section for Statistical Programmers and Analysts
|
|
Abstract #328767
|
|
|
Title:
|
Boost Your Analytical Power by Utilizing Text Data
|
|
Author(s):
|
Jin Su and Danielle Boree*
|
|
Companies:
|
Johnson & Johnson Vision Care and Johnson & Johnson Vision
|
|
Keywords:
|
unstructured data;
text analytics;
predictive modeling;
sentiment analysis
|
|
Abstract:
|
The volume of unstructured text data has grown exponentially in recent years. This presentation will discuss how statisticians have applied text analytics to tackle unstructured data in the medical device industry. Two case studies will be provided which demonstrate how text mining opportunities were identified, text mining models were built, and how these tools were deployed to solve real-world business problems. Case Study #1 will review how call center narratives were analyzed to predict the likelihood that they contained a reportable adverse event. Case Study #2 will review how online reviews and social media mentions were analyzed to extract customer sentiment and identify product quality improvement initiatives.
|
Authors who are presenting talks have a * after their name.
