Welcome to the resources page for analyzing social media data with R! These resources are based on multiple workshops given at Ludwig-Maximilians-Universität München (LMU) and the University of Georgia Digital Humanities Lab. Workshop materials: Here is a section of goodreads quotes, obtained via kaggle.com. Here is our handout for today. Here is the R code for today. Comments, questions, or suggestions? Email me at katherine.ireland@uga.edu

R and the Comprehensive R Archive Network (CRAN) R is a programming language for statistical computing, but it is useful for a wide variety of applications! It is maintained internationally by a team of developers through the Comprehensive R Archive Network (CRAN). In order to run your R code, you will first need to have R installed! Install R R runs on many different operating systems (OS); select the link below that corresponds to your needs.

This series of workshops will show participants their options to analyze text at scale. These sessions are open to all and are intended for beginners. No experience necessary. Sessions are held on Thursdays at 4pm via Zoom; contact DigiLab for the zoom information and link! April 1st: Text Analysis Basics April 8th: Text Analysis for Literature and Beyond April 15th: Creating your own Social Media Corpus April 22nd: Text Analysis Applications: Social Media

This glossary features definitions and recommended resources on text analysis. Anaconda: python data science platform. Useful for hosting Jupyter notebooks and other environments for testing and running your code. Artificial Intelligence/AI: interdisciplinary subfield of computer science; focuses on training computers and computational systems to perform a variety of tasks including decision-making, speech recognition, and translation tasks. Overlaps with some areas of Machine Learning and Natural Language Processing. Brown corpus: first text corpus of general American English, compiled Henry Kučera and W.

February 2021: Text Analysis Series This series of workshops will show participants their options to analyze text at scale. These sessions are open to all and are intended for beginners. No experience necessary. Sessions are held on Thursdays at 4pm via Zoom; contact DigiLab for the zoom information and link! Feb. 4th: Intro to text analysis resources at UGA and beyond Feb. 11th: Intro to text analysis with Jupyter notebooks and python Feb.

At the University of Georgia Digital Humanities Lab sponsored by the Willson Center, my colleague Keiko Bridwell and I are hosting Data Office Hours. More information available on the flyer below:

Links to a recording of each lecture, handouts, and the data used for tutorials are available here. Data Visualization Lectures, Fall 2020 Lecture 3 is on scatterplots in Excel, Tableau, and R.

Data Visualization Lectures, Fall 2020 Lecture 2 is on bar graphs and histograms in Excel, Tableau, and R.

Access the pdf and information about the first lecture in a series on Data Visualization, given at the University of Georgia Digital Humanities Lab, sponsored by the Willson Center. Links to a recording of each lecture, handouts, and the data used for tutorials are available here. Data Visualization Lectures, Fall 2020 Lecture 1 is an introduction to data visualization and resources at UGA.

Here is a link to the tutorial I created in collaboration with Camila Livio, PhD candidate in Romance Linguistics at UGA, for R Ladies Athens and #dayofDH2020. Camila discusses R packages for getting twitter data and analyzing different languages, udpipe and rtweet including Spanish and Portuguese, for text mining and analysis, and I write about the gutenbergr package, one of my favorites for text analysis in R!