Workshop: Introduction to Quantitative Text Analysis using R › view all

Joint SOCIUM and BIGSSS “Quantitative Text Analysis” Event Series

This workshop with Stefan Müller from Trinity College Dublin offers a hands-on introduction to extracting data from text, and applying various methods to analyse the data. Topics included involve:

• From Raw Text to Corpus – how to collect textual data and prepare it for analysis.
• Classification techniques - the first steps in translating text to usable data; supervised and unsupervised learning; dictionary approaches and topic modelling.
• Scaling – Supervised and Unsupervised techniques.
• An overview of more advanced topics.

The applied elements of the workshop will make use of the programming language R. * Therefore, a basic familiarity with R is a prerequisite for attending the course.* Note, that there is a vast amount of online tutorials and resources for learning R, among them https://www.datacamp.com/ or https://resources.rstudio.com/ that we recommend in the run-up. Also, attendance at the R Refresher is recommended for all participants.

Registration: NUMBER OF PLACES (WORKSHOP) RESTRICTED, SO PLEASE ONLY REGISTER (ASAP) IF YOU ARE PREPARED TO ACTIVELY ENGAGE AND ATTEND ALL SESSIONS: BIGSSS fellows register via CampusNet, SOCIUM members please send a short email to m.larsen@jacobs-university.de)

On the “Exploring Text as Data: Quantitative Text Analysis” Event Series

Can words be used as data? Social scientists are increasingly faced with large quantities of text – among them electoral manifestos, twitter feeds, press statements and interviews.  Moving beyond traditional, qualitative approaches to analysing them, researchers have started using the huge volumes of text available electronically to their advantage to test theories about the world. SOCIUM and BIGSSS are therefore happy to present the “Exploring Text as Data: Quantitative Text Analysis” event series, to engage with this new frontier of social science research.