Text Analysis with Antconc

Workshop Leader: Andrew Salway

This is an online event which will be held via zoom. A zoom link will be sent out to registered participants before the workshop.

This workshop is for researchers who would like to use automated techniques to analyse the content of one or more text data sets (corpora), and to identify their distinctive linguistic characteristics and reveal new potential lines of inquiry. The text data could comprise thousands to millions of words of e.g. news stories, novels, survey responses, social media posts, etc. We’ll be using AntConc which is one of the most popular and well supported corpus analysis toolkits, and which is free to use.

The running example in the workshop will be a sample of the nine million tweets distributed by Twitter because they are thought to have originated from Russian trolls involved in election and referendum interference. You are also welcome to bring your own text data to work with.

We will use AntConc to make frequency lists, keyword analyses, sorted concordances, n-grams and word clusters, and collocation data. We will also briefly discuss what can be interpreted from the results of such analyses under the rubrics of discovery science and corpus-based discourse analysis.

The workshop is open to everybody. No prior experience with AntConc or text analysis will be assumed. Participants from outside of the University of Sussex are also welcome.

In advance of the workshop you will need to download some software and data files. Instructions can be found here: https://drive.google.com/file/d/1HZ8qU1XT_Qs2jiGltqgpW0AaX4qY8gpb/view?usp=sharing

If you have any questions, email a.j.salway@sussex.ac.uk

SHL Open Workshop: Text Analysis with Antconc