Collecting and Handling Open-Source Data for Natural Language Processing

text with annotations

 

In Person

This two-class course will focus on developing skills in Natural Language Processing (NLP) in Python, in the context of open-source data. 

The first session offers an introduction to NLP and the NLTK Python package. It will focus on the development of a basic scraper program to access text data from selected websites. Additionally, gathered data will be analysed for frequency and distribution to extract patterns and themes. The second session will focus on a complex application of text analysis to open-source data. 

This course ultimately supports the development of a practical and functional understanding of gathering and working with open-source data in the context of NLP for research purposes. Although the main focus of the course is textual data, key concepts explored in the workshops may be applied to speech and visual data. These will not be specifically explored in this course. 

This is an intermediate-level course. You will need to already understand programming, preferably in Python or R. Previous knowledge of NLP is not required. It is also not required to have previous knowledge of Google Colab, although it is encouraged to set up a Google account prior to the workshops. 

Those who have registered to take part will receive an email with full details on how to get ready for the course. 

After taking part in this event, you may decide that you need some further help in applying what you have learnt to your research. If so, you can book a Data Surgery meeting with one of our training fellows. 

More details about Data Surgeries. 

If you’re new to this training event format, or to CDCS training events in general, read more on what to expect from CDCS training. Here you will also find details of our cancellation and no-show policy, which applies to this event. 

 

If you're interested in other training on text analysis, have a look at the following: 

Return to the Training Homepage to see other available events.

Digital Scholarship Centre

Digital Scholarship Centre, 6th floor

Main Library 

University of Edinburgh 

Edinburgh EH8 9LJ

You might be interested in

Analysing Polarisation in Political Texts

Analysing Polarisation in Political Texts

Interactive Analysis Reports with R Markdown

Interactive Analysis Reports with R Markdown

Gale Digital Scholar Lab Workshop

Gale Digital Scholar Lab Workshop

Introduction to Bayesian Statistics

Introduction to Bayesian Statistics

text analysis

Digital Method of the Month: Text Analysis

Manuscript

Getting Started with Transkribus

Beyond Social Networks with Gephi

Beyond Social Networks: Advanced Uses of Gephi in Humanities Research

Advanced Uses of LLM

Advanced Uses of LLMs