Can you teach a machine to understand emotion? It’s actually a lot easier than it sounds!
In this talk, I will show you how to iteratively build an AI-powered pipeline for Twitter sentiment analysis. A PhD in statistics is not required: we’ll start with a simple model and build towards more complex and powerful solutions.
I lead the data science team for Connected Converged Security at Johnson Controls. In my job, I design reliable AI-powered solutions that protect people, places and things. At home, I like to tinker with data and sometimes I even learn something useful.
Previously, I lectured on data analytics at the Department of Computer Science at CIT and spent two years as a data scientist and software engineer at IBM, where I developed machine learning algorithms for their Operations Analytics - Predictive Insights product. I also have a PhD in Electrical and Electronic Engineering from UCC, for which I developed several compute-friendly statistical models of radio system behaviour and wrote a lot of bad code.