👨‍🏫 Week 11 - Unstructured Data

DS105 - Data for Data Science

Here’s what to expect from this week’s lecture (and the week):

• On the first hour of the lecture, Prof. Ken Benoit will demonstrate how to implement a data pre-processing pipeline, using his study of Brexit Tweets as a case study.
  • This will feature: data acquisition, cleaning, tokenisation, and feature selection
  • But he will also show the outputs from topic models, sentiment analysis, and networks of hashtags and topics.
• On the second hour of the lecture, I will show you how to work further with network data. This will include a tutorial of the igraph library.

Come back later to view links to slides/code we have used in the lecture.