
Text as Data: Using Generative AI for Quantitative Content Analysis
This intermediate-level workshop introduces doctoral researchers in the social sciences to the emerging applications of generative AI for quantitative content analysis. Participants will explore how large language models (LLMs) can be integrated into established research workflows to enhance, extend, and innovate approaches to analysing text-based data.
The first session provides a concise overview of traditional quantitative content analysis methods and introduces the core concepts behind generative AI, with a focus on understanding how LLMs operate. Building on this foundation, we will explore practical strategies for applying generative AI tools, including OpenAI’s API, to automate and scale coding tasks, extract thematic patterns, and generate structured data from unstructured text.
The second session will emphasise hands-on application, including live demonstrations and guided exercises using R and OpenAI’s API. Participants will also critically engage with issues of reliability, bias, and validation when using AI-assisted content analysis, learning practical techniques to assess and improve the quality of outputs.
This is a highly applied workshop intended for researchers who have some familiarity with coding (e.g., Python or R) and want to deepen their methodological toolkit by incorporating AI-driven approaches into their projects.
By the end of this workshop, participants will be able to:
- Evaluate the principles and limitations of quantitative content analysis and how generative AI can be applied within this framework;
- Describe the capabilities and operational principles of large language models (LLMs) relevant to text data research;
- Use OpenAI’s API to conduct automated content analysis tasks on text datasets;
- Validate AI-generated outputs using appropriate techniques to ensure rigour and reliability;
- Reflect critically on the ethical, methodological, and practical considerations of integrating generative AI into social science research.
This training session will be delivered in person only at the University of Sheffield.
Bookings will close at 9am on Monday 2nd June.
As places are limited, please book a place only if you are sure that you will be able to attend.
When booking, you must use your institutional (.ac.uk) email address and complete all fields of the booking form. Your booking will otherwise be cancelled, and you will need to re-book (subject to availability). Thank you for your understanding.