Bootcamps » TEXT MINING AND SENTIMENT ANALYSIS

Description

This full-day, advanced-level bootcamp teaches you how to design, build, and implement text-mining applications to analyze and visualize real-world consumer sentiments using AWS services and tools such as R. The bootcamp includes topics such as ingesting data from Twitter feeds in real time; analyzing the data using text-mining techniques provided by R; storing and interactively querying the data on AWS using services such as Amazon S3, Amazon Redshift, Amazon Athena, Amazon Elasticsearch Service (ES), and Amazon Kinesis Firehose; and visualizing the data using RStudio and Amazon QuickSight.

Objectives

This bootcamp teaches you how to:

  • Collect and prepare textual data for the purposes of text mining and sentiment analysis.
  • Analyze the text using text-mining techniques and sentiment packages provided by R, one of the most popular tools for data analytics.
  • Visualize the data in RStudio using techniques such as topic modeling and clustering of data.
  • Ingest the data using Kinesis Firehose and store in Amazon Redshift, Amazon ES, and Amazon S3 for further analysis.
  • Query and explore the data interactively using Amazon Redshift and Athena.
  • Search a collection of text documents with Amazon ES, using features such as full text search.
  • Visualize the data using Amazon QuickSight and analyze trends over time.
  • Apply the knowledge gained to hands-on labs that provide practical experience with building an end-to-end text-mining solution to analyze real-world consumer sentiments.

Intended Audience

This bootcamp is intended for:

  • Solutions architects
  • Data scientists
  • Big data developers and engineers
  • Data architects
  • Marketing and data analysts
  • Other hands-on data and analytics practitioners

Prerequisites

We recommend that attendees of this bootcamp have the following prerequisites:

  • Good working knowledge of AWS core services, including Amazon Elastic Compute Cloud (EC2) and Amazon Simple Storage Service (S3)
  • Working knowledge of AWS services such as Amazon EMR, Amazon Redshift, Athena, Amazon ES, and Kinesis Firehose
  • Some experience working with the R programming language
  • Familiarity with the Linux operating system and command line interface

Delivery Method

This bootcamp is delivered through a mix of:

  • Instructor-Led Training (ILT)
  • Hands-On Labs

 

Note: A laptop is required in order to complete technical lab exercises; tablets are not appropriate.

Duration

One day

Outline

This bootcamp covers the following concepts:

  • Key services and tools that help build a text mining application on AWS
  • Pre-processing of textual data using cleansing techniques provided by the R programming language
  • Text-mining concepts using techniques such as sentiment analysis, topic modeling, clustering, and classification of text
  • Data ingestion and delivery capabilities provided by Kinesis Firehose
  • Interactive analysis of data using SQL capabilities provided by Amazon Redshift and Athena
  • Search capabilities provided by Amazon ES
  • Data visualization techniques using RStudio and Amazon QuickSight
  • Repeatable template deployment for implementing a text-mining application on AWS