Sentiment Pipeline for Live Tweets

This will be an advanced talk on how to build a real-time predictive analytics pipeline. This will be a two hour talk and demo that covers the following:

• Building a sentiment classification model in Azure ML and R from a supervised Twitter dataset
• Setting up an automated text processing pipeline in the cloud using Azure ML and R
• Setting up an elastic scaling web service endpoint for your predictive model in Azure ML
• Opening up a live twitter stream using Python
• How to ingest the twitter stream into Azure messaging queues via Python
• Hooking up stream processors to your queues and referencing your deployed predictive web service
• Real-time dash boarding with PowerBI and C#

Supplementary Material found here

More Data Science Material:
[Video Series] Beginning R Programming
[Video Series] Introduction to Azure Machine Learning Studio
[Blog]  Power BI and R: Intro to Visualizations
[Blog] High Dimensional Data: Breaking the Curse of Dimensionality with Python


Phuc H Duong
About The Author
- Phuc holds a Bachelors degree in Business with a focus on Information Systems and Accounting from the University of Washington.


You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>