Workshop on Social Media and Demographic Research - IUSSP - Cape Town 2017
This repository contains the materials prepared by Emilio Zagheni 1 and Connor Gilroy 1 for the IUSSP 2017 Workshop on Social Media, Big Data and Digital Demography.
Please complete the following setup steps before the workshop. If you run into trouble with one of them, please attempt to complete the others.
This is an approximate schedule for the day-long workshop.
| 8:30-9:00 | Introduction |
| 9:00-10:00 | Lab: APIs |
| 10:00-10:15 | Break |
| 10:15-11:45 | Lab: Twitter |
| 11:45-12:45 | Lunch |
| 12:45-13:30 | Lab: Twitter + Visualization |
| 13:30-14:15 | Using Facebook Ads for research |
| 14:15-14:30 | Break |
| 14:30-15:30 | Lab: Facebook Ads |
| 15:30-16:00 | Discussion |
The linked folders and repositories contain the code and slides for the hands-on modules.
| Module 1 | Retrieving data through APIs |
| Module 2 | Collecting and analyzing Twitter data |
| Module 3 | Visualizing and mapping Twitter data |
| Module 4 | Demographic estimates from the Facebook Marketing API |
These are additional resources you may find useful as you continue to learn about R and about digital demographic methods. R has a generous and welcoming community of users, and they have made many materials for learners available freely online.
Charles Lanfear teaches a 10-week course at the University of Washington called Introduction to R for Social Scientists. The slides and recorded videos of his lectures are publicly available on his course website: https://clanfear.github.io/CSSS508/
R for Data Science is a focused and clearly-written introduction to working with R by Garrett Grolemund and Hadley Wickham. These authors have also written other books you may find helpful. The entire book is available freely at this website: http://r4ds.had.co.nz/
Kieran Healy's new book, Data Visualization for Social Science, introduces
you to principles of good graphics and to plotting in R using ggplot2.
It is available online at this website: http://socviz.co/
If you are interested in working with text data and continuing to do sentiment analysis, a helpful book is Text Mining with R, by Julia Silge and David Robinson. Their chapter on sentiment analysis describes three different common dictionaries for sentiment in English-language texts. The book is online at this website: http://tidytextmining.com/
All of the above resources are free. We have typically found these types of resources to be more than adequate for our own learning and teaching. However, you might prefer to use more interactive or elaborate learning materials. In that case, one paid resource for learning data science in R online is DataCamp. Some university departments in the United States use their courses as additional materials for teaching students R. You can try out one of their courses, Introduction to R, for free, to see if you prefer that style of teaching and learning.
1: University of Washington