When I spent some time with the HP Vertica team at the MIT Sloan Sports Analytics Event earlier this month they told me about a Sentiment Tracker they were working on in prep for the NCAA March Madness countdown of 64 college teams which starts tomorrow. Various HP Software resources from Autonomy, HP Vertica, and HP Information Management & Analytics (IM&A) were involved in the project.
The analysis looked at roughly half a million Tweets using Autonomy’s data aggregator, crunching the data using Vertica and visualization (like below) using Tibco Spotfire:
- Volume of tweets by team
- Volume of tweets by player
- Positive, negative, and neutral sentiment groupings
- Volume of tweets by U.S. city and by worldwide country
- Volume of tweets by language (English, French, Spanish, etc.)
How is that going to help with your "bracketology"?
As Jeff Healey of Vertica asks here "why not use HP Vertica’s tight integration with R to develop a statistical model based on data available from ESPN and the likes on hard basketball statistics, such as field goal percentage, points allowed, head-to-head scoring, and more? You could correlate that statistical data with sentiment data trending from Twitter."
Or you could just put your finger in the air and let it pick your squares like you have done forever:)
Click image twice to enlarge
Comments