Introduction to Computational Text Analytics

Introduction to Computational Text Analytics

Martin Schweinberger and Sam Hames

Do you have more text than you know what to do with? Did you collect data including text for your project and now feel overwhelmed when you try to analyse? Is there too much? Are you doing the same thing over and over again and feeling like you're not using your time efficiently? Are you worried about missing the forest for the trees (or the trees for the forest)? If any of these apply to you (or you're just interested in learning more) this workshop is for you.

This workshop will introduce the fundamentals of computational text analysis using LADAL. We'll start with the key questions of why and where computational methods might be appropriate for your work before moving onto the how. For the how we will:

1.  Outline the necessary preparation and preconditions for using computational approaches to text.
2.  Introduce you to the R programming language with Jupyter notebooks.
3.  Guide you through using a series of common methods and libraries in R so you can start asking the right questions for your own projects.
4.  Tie everything back together with a discussion of the practical aspects of managing projects with computational components grounded in our research experiences.

Preparation

Participants will need to bring a laptop with internet access. No installation will be necessary for the practical parts of this workshop as we will be using an online environment with all components pre-installed.

You are welcome to bring your own data and projects to try to work through the materials with (however data preparation is usually a big part of using computational methods, so we may not have time in the workshop to get everything working for you).

About LADAL

LADAL, the Language Technology and Data Analysis Laboratory is an online platform for computational humanities upskilling that provides resources that allow users to perform analyses using R. LADAL is part of the Australian Text Analytics Platform (ATAP) and the Language Data Commons of Australia (LDaCA) that are funded by the National Research Infrastructure for Australia (NCRIS) and the Australian Research Data Commons (ARDC).

The resources offered by LADAL encompass explanatory online tutorials, interactive Jupyter notebooks that accompany the tutorials, and notebook-based online tools that allow users to apply methods described in the tutorials to their own data.