Text Analytics from a galaxy far, far away PRESENTED BY: - PowerPoint PPT Presentation

Text Analytics from a galaxy far, far away PRESENTED BY: C.BATTISTON TASS MEETING, JUNE 21, 2019

What is Text Analytics?  Text analytics is the way to unlock the meaning from all of this unstructured text. It lets you uncover patterns and themes, so you know what customers are thinking about. It reveals their wants and needs.  "Text analysis" is a broad term covering various processes by which text and natural language documents can be modified so that they can be organized and described.

What is “Star Wars”?  Overall premise: The Rebellion Alliance is fighting against the evil Galatic Empire.  Characters:  Good guys – Luke Skywalker, Princess Leia, Han Solo, Ben Kenobi, C3P0  Bad guys – Darth Vader, The Emperor. The Death Star is the main space station / weapon of the Empire.

Data for this presentation  Data was found at https://github.com/gastonstat/StarWars/tree/master/Text_files  Requires copying and pasting into Excel or a TXT file, whichever your preference.

Preparing/Cleaning the Data (Excel-based)

Import and Data Manipulation

Cleaning some of the data in SAS There were a number of different UPDATE statements I ran to clean the data, but they all had the same basic format.

Analysis – Line Counts

Analysis – Usage of the word “Force”

Analysis – Amount of text spoken

Which characters’ lines were the longest?

References and Recommended Reading  Text Mining and Analysis: Practical Methods, Examples, and Case Studies Using SAS by by Goutam Chakraborty, Murali Pagolu, Satish Garla  SAS Essentials: Mastering SAS for Data Analytics by Alan C. Elliott, Wayne A. Woodward  A simple approach to text analysis using SAS functions by Wilson Suraweera, Jaya Weerasooriya, Neil Fernando https://www.sas.com/content/dam/SAS/support/en/sas-global-forum- proceedings/2018/2557-2018.pdf  Text Mining of Open-Ended Survey Data by Brandon J. Hosek, MA, Barbara E. Wojcik, PhD https://www.sas.com/content/dam/SAS/support/en/sas-global- forum-proceedings/2019/3705-2019.pdf

Thanks and Contact Info You can reach me at: Darth.Pathos@gmail.com I’ve got to Han it to you, Yoda best audience!