Text Data Workshop

Presenter(s): Lewys Brace

decorative image with NCRM logo

The resource is broken down into three videos. Each video has a Jupyter notebook to accompany it and is aimed it at programming novices. The first video is a very brief intro to Python that covers the parts of the language you need to know to scrape and analyse text data, the second video cover how to build a basic web scraper and save textual data into a file, and the third video covers some very basic textual data analysis; i.e. bi-grams.

Text data workshop part 1

Dr Lewys Brace of the University of Exeter introduces Python in the first of three videos, providing a brief overview and explaining key elements of the software. Then, you can test your understanding by completing the tasks discussed in videos two and three of the series.

   Download transcript    |   [ 194 Views ]

Text data workshop part 2

In the second of three videos, Dr Lewys Brace builds upon a basic introduction to Python, looking at how to use knowledge to build a web scraper to scrape simple text data from a website.

   Download transcript    |   [ 153 Views ]

Text data workshop part 3

In this third and final part of the series on text data workshops, Dr Lewys Brace of the University of Exeter looks at how to carry out some basic text data analysis.

   Download transcript    |   [ 96 Views ]

About the author

Dr Lewys Brace is a Lecturer in Data Analysis and part of the University of Exeter's Q-Step Centre. He is also the academic lead for the Pathways to Data Analytics Programme.

His research focuses on both extremist radicalisation and the development of computational research methods. He has recently received a CREST award to conduct research on far-right online forums, with Dr. Stephane Baele and Dr. Travis Coan.

Primary author profile page