September 2018
Big Data Analysis for Social Scientists workshop - Social Informatics 2018 (St Petersburg, Russia)
This page provides resources for participants in the Big Data Analysis for Social Scientists workshop at Social Informatics 2018. The course is taught by Robert Ackland from the VOSON Lab (School of Sociology) at the Australian National University.
The workshop will introduce participants to two R packages/apps developed at the VOSON Lab: VOSON Dashboard (an R/Shiny app for collecting and analysing social media network and text data) and vosonSML (an R package for collecting social media network and text data). The data collection facilities in VOSON Dashboard are provided via vosonSML.
vosonSML (formerly known as "SocialMediaLab") collects Twitter and YouTube data from the respective free APIs. If you want to collect data you will need to arrange API access. You can find details on how to get API access here. Please note that we will not have time to cover setting up API access in the class. Please also note that as of July 2018, Twitter are manually vetting applications for API access and they can take up to 2 weeks for approval. Please also note that tutorial datasets will be provided in the course, so you can participate even without API access.
In order to participate in this workshop you will need to have the following installed:
- R statisitcal software
- RStudio. This is needed for running VOSON Dashboard (to use vosonSML you do not need RStudio).
- vosonSML R package. We will use the official CRAN version - the development version is here.
- VOSON Dashboard. This is not yet publicly released and so we will use a development version.
It it expected that you will already have some familiarity with R and RStudio - if not, the following may be of help: Rmd, pdf
While we will only be working with VOSON Dashboard in this workshop (we will not use vosonSML directly). If you want to use vosonSML directly, please see the following tutorial (note: this refers to "SocialMediaLab" the old name of the package): Rmd, pdf
Datasets
Demo WWW hyperlink datasets "DividedTheyBlog_40Alist_release.graphml" and "enviroActivistWebsites_2006.graphml" are provided in the VOSON Dashboard zip file.
Demo Twitter datasets: twitter_auspol_07Aug18.graphml.zip, twitter_auspol_07Aug18_with_text.graphml.zip