Let's analyze how world reacts to road traffic by sentiment analysis through twitter data

In this session you will build a sentiment analysis solution step by step, using Azure Platform. We will talk about sentiment analysis and how you can get this introduced in your application. We will run live demo and extract data from live twitter feeds and work together in processing the data and performing sentiment analysis on the data. We encourage audience to come with mobile phones to tweet :P but if not, not to worry as we can use the historical data.

Transcript

1. What can sentiment analysis through Twitter data really tell us? Colombo Big Data Meetup August 2nd 2018 Let’s analyze the world’s reaction to road traffic
2. In a nutshell Social Developer Skills & Interests Recognitions ❑ 7+ years experience ❑ Full stack developer ❑ Angular, Big Data enthusiast ❑ Automation fanboy ❑ Microsoft MVP Developer Technologies ❑ Top contributor in the world on Stackoverflow for #Angular, #Cosmosdb ❑ Web application architecture ❑ Business intelligence ✓ Big Data ✓ Visualization ❑ Azure platform ❑ 120 repositories on Stackblitz ❑ 4800+ answers on Stackoverflow ❑ Github contributions ✓ D3 directives and more Open-source contributions Sajeetharan Sinnathurai Senior Tech Lead at 99X Technology A few things about me!
3. What is sentiment analysis? “computationally identify and categorize the opinions expressed in a piece of text; determine whether positive/neutral/negative toward a topic/product…” [Oxford Dict.]
4. Why it is so important? • Monitor brand reputation • Crisis management • Competitive benchmarking • Marketing strategies • Product development “If you don’t understand their emotions, you don’t understand your customers”
5. Why Twitter Data? • 12+ TBs of tweet data • 500 million public opinions • Rich content (e.g. graph properties) 504,000,000 * 280 = 7,056,000,000 pages 2,352,000 books
6. Application Architecture • Sentiment Analysis in 2015 Collect Twitter Data Store Data Score Data Visualize Data Tweepy/Scrapy WareHouse Scikit-learn Visualize Data Pandas Visualization Tool
7. Application Architecture • Sentiment Analysis in 2018 Collect Twitter Data Score Data Store Data Visualize Data
8. What is Logic Apps? • Visual designer without writing single line of code • Dozens of pre-built templates to get started • Out of box support for popular SaaS and on-premises apps • Use with custom API apps of your own • Biztalk APIs for expert integration scenarios
9. Cognitive services Vision Speech Knowledge Language Search “Give your apps a human side”
10. •Sentiment analysis •Key phrase extraction •Topic detection •Language detection
11. It’s Demo Time
12. And we are done
13. Oh wait. Are we? Give away What were the two main Azure resources presented in this session? What is the name of the NOSQL database that could replace MSSQL in the proposed solution? What is the name of the Python library used for doing Data transformation in the earlier solution?
14. Thank you! https://www.rateevent.com/rate/SCAAA180 Stackoverflowers SriLanka: https://www.facebook.com/groups/879149618935395 @Kokkisajee