LLMs for Qualitative and Mixed-Methods Social Network Analysis
2026-07-15 • Social and Information Networks
Social and Information Networks
AI summaryⓘ
The authors explore how large language models (LLMs) can help in social network analysis (SNA), especially in understanding relationships and stories within networks. They emphasize that LLMs should support researchers rather than replace them, aiding tasks like data collection, coding, and developing theories. The authors also highlight potential problems like bias and errors in LLMs and stress the importance of careful and ethical use. Finally, they offer practical advice for researchers wanting to combine LLMs with qualitative and mixed-methods SNA.
Large Language ModelsQualitative Social Network AnalysisMixed-Methods ResearchData CodingTheory BuildingAbductive ReasoningBias in AIEthical AI UseRelational IdentitiesNarrative Analysis
Authors
Moses Boudourides
Abstract
This manuscript explores the integration of Large Language Models (LLMs) into the field of qualitative and mixed-methods social network analysis (SNA). We argue that the primary focus of this integration should be on enhancing the depth and rigor of qualitative SNA, rather than on replacing human researchers with automated systems. We begin by outlining the core principles of qualitative and mixed-methods SNA, emphasizing the importance of understanding the meaning of ties, the role of narratives, and the significance of relational identities. We then discuss how LLMs can be used as powerful tools to augment this work, from assisting with data collection and coding to supporting theory-building and abductive reasoning. We also address the limitations and ethical challenges of using LLMs in this context, including issues of bias, hallucination, and the need for reflexivity. We conclude with a series of research designs and practical recommendations for researchers who want to integrate LLMs into their work in a thoughtful and responsible way.