Experience in applying large language models to analyse quantitative sociological data

Abstract

Listen

Translate article

The article discusses the possibilities and limitations of using large language models (hereinafter referred to as LLM) to analyse quantitative data in sociological research. Also, attention is paid to the actor-network theory, according to which neural networks act as active participants of social interaction. It is noted that the usage of the LLM can be considered as an innovative process in the field of applied sociological research. The article demonstrates examples of the LLM application for quantitative methods of analysis on the basis of a survey dataset taken from open sources. Practical examples show how the LLM can be used to construct frequency and summary tables, calculate averages and conduct correlation analysis. The application of the LLM is seen as an innovative process that promotes the development of new methodological approaches. The authors analyse examples of the LLM usage in sociology and emphasise the need to build an innovative culture and develop methodological approaches to verify and correct the results. In addition, the authors highlight the importance of interpreting the LLM results in the context of sociological theory and practice. The article also discusses the role of the LLM in empowering the sociological research, especially in the areas of analysing big data and discovering hidden patterns. Finally, the authors suggest paths for future research in the application of the LLM in sociology, including the development of new methods and tools for integrating the LLM into the sociological research.