The workshop will focus on developing a batch-processing workflow rather than processing documents individually. By the end of the workshop, participants will have a better understanding of how to use Python to transform scanned documents and image-based PDFs into searchable text.
The workshop will focus on developing a batch-processing workflow rather than processing documents individually. By the end of the workshop, participants will have a better understanding of how to use Python to transform scanned documents and image-based PDFs into searchable text.
The digital method of the month meeting is a safe space to freely discuss the practicalities of learning and implementing a new digital skill in your research. During this session, we will introduce the concept of Large Language Models (LLMs), discuss their strengths and weaknesses, and explore how they can be effectively integrated into research workflows.
The digital method of the month meeting is a safe space to freely discuss the practicalities of learning and implementing a new digital skill in your research. The method of this month is GIS, or Geographic Information Systems. GIS is a computer system that combines maps and databases to help people create, manage, and analyse information about places.
This workshop will introduce you to the framework of null hypothesis testing, a simple test of mean differences (t-test), p-values, what they really mean and how to adopt them in your research.
The digital method of the month meeting is a safe space to freely discuss the practicalities of learning and implementing a new digital skill in your research. A big part of conveying research results hinges on how these results are presented. Join us to discuss the main principles of effective and reproducible data visualisation.
Sentiment analysis is the process of determining whether a piece of writing is positive, negative or neutral. Its use has become relatively widespread, including being used to analyse customer feedback, social media, user surveys, and more. This workshop will cover how it works; pros and cons; using it on text, user feedback and online sources.
This workshop will focus on developing practical skills for summarising and exploring data using R or Python. The session will introduce key concepts in descriptive statistics, including measures of central tendency, measures of variability and data distributions.
This lesson teaches how to create a digital gazetteer from a historical text using the Linked Places Delimited (LP-TSV) format. A gazetteer records place names, spatial extents, and historical data, offering a structured knowledge system to connect places, events, and people across time. It is a key tool for spatial history and digital humanities.
This workshop aims to introduce the main strategies of prompt engineering including tips and certain practices to achieve optimal outputs with Generative AI (Gen-AI) tools. After providing a hands-on overview of prompt engineering, certain features of ChatGPT will be discussed for fostering the research practices.
The digital method of the month meeting is a safe space to freely discuss the practicalities of learning and implementing a new digital skill in your research. During this session we will discuss trade-offs regarding gains in productivity and the dangers of producing executable code; how the development of these tools changes the nature of learning to code; as well as best practices and strategies for exploring this safely.
Edinburgh Futures Institute (EFI) building, The University of Edinburgh, 1 Lauriston Place, Edinburgh, EH3 9EF
*Deliveries via West Entrance on Nightingale Way.
Email: efi@ed.ac.uk
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336, VAT Registration Number GB 592 9507 00, and is acknowledged by the UK authorities as a “Recognised body” which has been granted degree awarding powers.
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2021.