Text Analytics Essentials

Take our free course

bdu-course-images-11

Text Analytics Essentials

with James Priebe

Audience:
Analysts, developers, and administrators who are interested in text analytics.

Time to complete:
3 hours

Available in:
English

The analysis of emails, blogs, tweets, forums and other forms of unstructured text data constitutes what we call text analytics.  Text analytics is applicable to most industries; for example, if your company is suspicious about company secrets being leaked to competitors by employees, text analytics can help analyze millions of employees’ emails.  If you would like to find common pain points your customers face when using your products, you can analyze their comments and questions in forums. If you would like to measure positive or negative perceptions of a company, brand, or product, you can perform sentiment analysis using text analytics. This course teaches you the basics of text analytics.

Big Data University has been chosen by IBM as one of the issuers of badges as part of the IBM Open Badge program. Share your achievements through LinkedIn, Facebook, Twitter, and more! See more at: http://bigdatauniversity.com/bdu-wp/bdu-course/text-analytics-essentials/

Big Data University leverages the services of Pearson VUE Acclaim to assist in the administration of the IBM Open Badge program.  By enrolling into this course, you agree to Big Data University sharing your details with Pearson VUE Acclaim for the strict use of issuing your badge upon completion of the badge criteria.

This course was tested and validated for v3 of the QSE VM. Please download the v3 VM to complete the lab exercises.

https://www14.software.ibm.com/webapp/iwm/web/preLogin.do?source=swg-beta-iibob

 

Course Syllabus

After completing this course, you should be able to:

  • Describe the approach for doing text analytics
  • List the task analysis steps
  • Label clues in your documents that will help you to create your extractor
  • Describe the AQL data model
  • List the AQL components
  • List the AQL objects that are used to create basic features
  • Create basic features views
  • Remove XML and HTML elements from a document using the Detag statement
  • List the AQL candidate generation components
  • Create candidate generation views
  • List the AQL filter and consolidation objects
  • Create and export an AQL module

General Information

  • This course is free.
  • It is self-paced.
  • It can be taken at any time.
  • It can be taken as many times as you wish.
  • Labs can be performed on the Cloud, or using a 64-bit system. If using a 64-bit system, you can install the required software (Linux-only), or use the supplied VMWare image.
  • More details are provided in the section "Labs setup".
  • Students passing the course (by passing the final exam) will have immediate access to printing their online certificate of achievement.
  • Your name in the certificate will appear exactly as entered in your profile in BigDataUniversity.com.
  • If you did not pass the course, you can take it again at any time.

Pre-requisites

Before taking this course, you should have the following background:

  • Have taken the Hadoop Fundamentals – Version 3 on Big Data University

Recommended skills prior to taking this course

  • Basic understanding of Apache Hadoop and Big Data.
  • Basic Linux Operating System knowledge

Grading Scheme

The minimum passing mark for the course is 60%, where the final test is worth 100% of the course mark. You have 3 attempts to take the test