In this unit we will see how to collect data from Twitter and YouTube. The unit will start with an introduction to Python programming. Then we will use a Python script, with a little editing, to extract data from Twitter. A similar exercise will then be done with YouTube. In both the cases, we will also see how to create developer accounts and what information to obtain to use the data collection APIs. Once again, make sure to go item-by-item in the order provided. Before beginning this unit, ensure that you have all the right tools (Python, R, Anaconda) ready and configured. The lessons depend on them and also your ability to install required packages.

In this unit, we will focus on analyzing and visualizing the data from various social media services. We will first use the data collected before from YouTube to do various statistics analyses such as correlation and regression. We will then introduce R - a platform for doing statistical analysis. Using R, then we will analyze a much larger dataset obtained from Yelp. Make sure you have covered the material in the previous units before proceeding with this. That means, having all the tools (Anaconda, Python, and R) as well as various packages installed. We will also need new packages this time, so make sure you know how to install them to your Python or R. If needed, please review some basic concepts in statistics - specifically, correlation and regression - before or during working on this unit.

In the final unit of this course, we will work on two case studies - both using Twitter and focusing on unstructured data (in this case, text). The first case study will involve doing sentiment analysis with Python. The second case study will take us through basic text mining application using R. We wrap up the unit with a conclusion of what we did in this course and where to go next for further learning and exploration.