Sentiment Analysis on Twitter Data: Hadoop, Spark, NOSQL

To expedite check-in on the day of the meetup, please pre-register HERE. (https://www.eventbrite.com/e/sentiment-analysis-on-twitter-data-hadoop-spark-nosql-tickets-28392776559)

In this era of social transparency and cognitive thinking, we would like to invite you to join us for a demonstration of how to analyze customer sentiment while leveraging Hadoop, Spark, and a NoSQL Database on the cloud.

You will learn how a data pipeline can be built using tools and technologies available on Bluemix (cloud offerings), while experiencing the value of having many tools working seamlessly together to provide a solution that goes from accessing source data to transforming it into a consumable format (report, API, visualization, etc.). You will also see how an Analytics team can make better use of data with a sustainable architecture. We will be adding a load of about 10 years’ worth of historical data as well, to do the analysis of movie series, actors/actresses, etc. Our focus is on the architecture, pipeline and output, to ensure that teams can:
• Focus less on gathering and organizing the data
• Access a platform where multiple tools and approaches can be used to analyze the data
• Generate executive summaries for consumption of insights from a broad audience.

Presenter Bio:
Suresh Matlapudi is an Open Source Analytics Solution Engineer with IBM. He is a hands-on Engineer with deep experience in distributed data processing, Big Data and Data Warehousing to deliver Hybrid Information Architecture. His current work involves supporting sales team with pre-sales and technical specification for Open Source Analytics tools, specifically the Hadoop/Spark and execution of several outreach programs to support Open Source adaptation by Analytics teams. Before joining with IBM he was involved in building some of the large-scale data processing systems at companies like eHarmony, Deem, American Express, Knights Bridge Solutions.

Limited Capacity - register soon.