Text-mining is one of many data-mining techniques that social scientists are using to turn unstructured (or more accurately, semi-unstructured) material into structured material that can be analysed statistically. In this way, researchers are gaining access to new materials and methods that were previously unavailable. As such, it is increasingly important that social scientists have a clear understanding of what text-mining is (and what is isn't) as well as how to use text-mining to achieve some basic and more advanced research outcomes.
The following topics are covered under this training series:
- Introduction to Text-Mining - covers the concepts behind fully structured and semi-unstructured data, the theory behind capturing and amplifying existing structure, and the four basic steps involved in any text-mining project.
- Text-Mining: Basic Processes - learn how to do some of the most common text-mining analyses using Python.
- Text-Mining: Advanced Options - understand the concepts behind more advanced text-mining analyses.
The training materials - including webinar recordings, slides, and sample Python code - can be found in the following folders:
- code - run and/or download text-mining code using our Jupyter notebook resources.
- webinars - watch recordings of our webinars and download the underpinning slides.
We are grateful to UKRI through the Economic and Social Research Council for their generous funding of this training series.
- To access learning materials from the wider Computational Social Science training series: [Training Materials]
- To keep up to date with upcoming and past training events: [Events]
- To get in contact with feedback, ideas or to seek assistance: [Help]
Thank you and good luck on your journey exploring new forms of data!
Dr Julia Kasmire and Dr Diarmuid McDonnell
UK Data Service
University of Manchester