This afternoon, we have a couple of topics to explore:

• A sentiment analysis exercise using the VADER module and very clean Twitter data
• A less processed Twitter dataset that will let us practice working with dictionaries

I will share that I completely changed my plans for today based on how quickly you were all absorbing Python yesterday, and it took quite a bit of time making sure I could download the necessary datasets and run the code I am sharing with you. This means we are in for a bit of an adventure, especially with the last dataset planned for the day, as I have not pre-tested a set of tasks for you. Instead, you will have the opportunity to act as the data scientist and try to determine what useful or interesting information can be pulled from these datasets.

You are also welcome to try to pursue a topic of personal interest to you. If you find datasets and code online, I will try to assist you in figuring out whether/how it might be usable for your purposes.

If we have additional time, here is another dataset we could explore:

Information about this dataset is provided here.

This is a large dataset, so we'll see how it goes.

Just in case, a smaller sampling is provided here.