Applied large language models for social science research
Date:
04/03/2026
Organised by:
London School of Economics and Political Science
Presenter:
Dr Zach Dickson
Level:
Intermediate (some prior knowledge)
Contact:
Description:
Training for PhD and MSc students in the design of social research, quantitative and qualitative analysis.
Applied large language models for social science research by Dr Zach Dickson.
This course will introduce students to the use of language models for social science research. Language models are a type of machine learning model that can be used to analyze text data. They have been used in a wide range of applications, from sentiment analysis to machine translation, and have especially gained spotlight following the launch of OpenAI's ChatGPT.
In this course, we will focus on how language models can be applied to social science research. We will cover topics such as embeddings, text classification, topic modeling, and text generation. We will also learn how to use language models to create training data, and we will discuss methods for evaluating the accuracy of language models and reporting metrics in academic research. Finally, we will consider the limitations and ethical implications of using language models in social science research.
By the end of the course, students will have a solid understanding of how to apply language models to their own research projects. A basic knowledge of programming in Python is recommended for this course.
Session Details
Time: 10:00 - 15:00 (12:00 - 13:00 Lunch break)
Date: 4 March 2026.
Mode: In-person only at CON 1.01
If you are an ESRC funded student then we require your name, email and course to report your attendance to your home institution, please click here to see the privacy notice that this data collection is subject to.
Cost:
Free
Website and registration:
Region:
Greater London
Keywords:
AI and machine learning
Related publications and presentations from our eprints archive: