AI for Qualitative Research
A Hands-On Guide for Management Scholars
- Open Access
- 2026
- Open Access
- Buch
- Verfasst von
-
Diana Garcia Quevedo
Diana Garcia Quevedo
- Center of Research in Sustainability (RESET), ESCP Business School, Paris, France
-
Josue Kuri
Josue Kuri
- Principal Scientist, San Francisco, USA
- Verlag
- Springer Nature Switzerland
Über dieses Buch
Dieses Open-Access-Buch wird qualitativen Forschern in den Sozialwissenschaften mit wenig bis gar keiner Kodierungserfahrung bei der Nutzung großer Sprachmodelle (LLMs) als Leitfaden dienen. Als Reaktion auf den Mangel an Unterrichtsmaterialien, die die Notwendigkeit erkennen, qualitative Forscher mit den fortschrittlichsten Werkzeugen auszustatten, bietet dieses Buch einen forschungsorientierten Leitfaden, um die Macht von LLMs nutzbar zu machen. Der Inhalt ist in zwei Teile gegliedert, beginnend mit einer Einführung in LLMs, natürliche Sprachverarbeitung und maschinelles Lernen sowie einer historischen und ethischen Perspektive auf den Einsatz künstlicher Intelligenz in der Forschung. Der zweite Teil des Buches dient als praktischer Leitfaden, der Schritt für Schritt Anleitungen für den Einsatz von LLMs zur Analyse großer Datensätze liefert. Es ist mit praktischen Fallbeispielen aus der Managementwissenschaft verfasst und betont die Aufrechterhaltung einer engen Verbindung zu den Daten während des gesamten Prozesses. Sie wird für Forscher in Managementstudien ebenso wertvoll sein wie in den Sozialwissenschaften im weiteren Sinne.
Mit KI übersetzt
Über dieses Buch
This open access book will guide qualitative researchers in the social sciences with little to no coding experience in leveraging large language models (LLMs). Responding to a lack of instructional materials that recognize the need to equip qualitative researchers with the most advanced tools, this book offers a research-focused guide to harness the power of LLMs.
The content is divided into two parts, beginning with an introduction to LLMs, natural language processing, and machine learning, as well as a historical and ethical perspective on the use of AI in research. The second part of the book serves as a hands-on guide, providing step-by-step instructions for the use of LLMs to analyze large datasets. It is written with practical cases, taken from management sciences, and emphasizes maintaining a close connection to the data throughout the process. It will be highly valuable to researchers in management studies, as well as in the wider social sciences.
Anzeige
Inhaltsverzeichnis
-
1. Introduction
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter explains the book’s objective, its structure, and additional resources provided within. It emphasizes the importance of understanding the technology underlying large language models to leverage their capabilities effectively. -
Part I
-
Frontmatter
-
2. Overview of Artificial Intelligence, Machine Learning, Natural Language Processing, and Large Language Models
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter provides an overview of the technology underpinning large language models (LLMs). It introduces the historical context of artificial intelligence (AI), from symbolic systems to statistical approaches and deep neural networks, highlighting milestones in natural language processing (NLP). It also addresses the limitations of LLMs, such as hallucinations, biases, and a lack of explainability, and the different types of LLMs according to their information-sharing approaches. The chapter aims to help readers understand LLMs and their underlying algorithms, setting the stage for a deeper exploration of ethical considerations and applications in subsequent sections of the book. -
3. Natural Language Processing in Management Research
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter highlights the evolving role of natural language processing (NLP) in management research. Although NLP has been utilized for decades, its full potential remains largely untapped, primarily concentrated in information systems and marketing for quantitative analysis. The chapter discusses how advancements in large language models (LLMs) have facilitated the integration of sophisticated NLP algorithms into qualitative research, enabling a more nuanced analysis of contextual meaning and the potential for richer theory development. Recent studies employing mixed-method approaches have demonstrated the ability of LLMs to enhance qualitative analysis, providing researchers with examples of the application of LLMs in qualitative research. -
4. Ethical Considerations
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter addresses the ethical implications of employing large language models (LLMs) in research contexts, highlighting the increasing importance of responsible artificial intelligence (AI) use. By focusing on the integration of LLMs in the context of research methodologies, this chapter outlines specific ethical challenges, including algorithmic bias, data privacy concerns, and the inherent lack of transparency and explainability in LLM outputs. This emphasizes the necessity for researchers to rigorously validate LLM-generated outputs and maintain a balance between leveraging the efficiency of AI and preserving the richness of qualitative analysis. Ultimately, the chapter advocates for a knowledgeable and critical approach to using LLMs, fostering an informed research community that values ethical standards in the application of AI technologies.
-
-
Part II
-
Frontmatter
-
5. Systems and Tools to Use NLP and LLMs: Getting Started
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter introduces essential systems and tools for leveraging various natural language processing (NLP) tasks and large language models (LLMs) in qualitative analysis, emphasizing accessibility for noncoders. It begins with an overview of the Python programming language and introduces tools such as the Pandas library, integrated development environments (IDEs), Jupyter notebooks, and application programming interfaces (APIs) for accessing LLMs. A second section provides a hands-on guide for setting up a computer environment, with step-by-step code examples designed to familiarize readers with NLP libraries and LLMs. It emphasizes the acquisition of programming skills to better adapt and utilize LLM capabilities for qualitative data analysis while providing multiple resources for further learning. -
6. Using LLMs in Qualitative Analysis
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter presents the method developed by Garcia Quevedo et al. in Organizational Research Methods (2025) for qualitative analysis of large, unstructured datasets using large language models (LLMs). It addresses the limitations of traditional random sampling by proposing a structured approach that efficiently explores and selects relevant data for manual analysis. The method integrates three natural language processing (NLP) tasks: sentiment analysis, topic modeling, and information retrieval, allowing for comprehensive dataset exploration and selection. These tasks are covered in the subsequent chapters. -
7. Data Evaluation and Validation
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter provides code examples for data evaluation and validation, introducing two approaches: traditional coding and large language model-based approaches. This chapter provides a concrete example of the limitations of large language models (LLMs), particularly in terms of reliability for numerical tasks. Researchers are advised to critically evaluate LLM outputs and consider traditional programming techniques for tasks that require numerical accuracy. -
8. Classification
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter provides an overview of classification, a key method in data analysis. It explains different techniques for data classification using large language models (LLMs), including open-access models and detailed prompts for zero-shot, one-shot, and few-shot classifications. The chapter illustrates how LLMs can enhance qualitative analysis by leveraging their classification capabilities. Additionally, the chapter discusses the importance of prompt design and the cautious use of LLMs. This suggests techniques for improving reliability and the use of balanced approaches when selecting methods for specific research objectives. -
9. Clustering and Topic Modeling
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter presents clustering and topic modeling as important techniques in natural language processing (NLP) for qualitative research. It highlights topic modeling as a specialized form of clustering aimed at uncovering hidden thematic structures within text datasets. Large language models (LLMs) improve the interpretability and coherence of topics compared with traditional methods. This chapter also addresses limitations such as topic instability and model hallucinations. Practical code examples illustrate the implementation of topic generation and assignment, thereby fostering a deeper understanding of the applicability of this NLP task in qualitative analysis. -
10. Information Retrieval and Retrieval-Augmented Generation
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter introduces information retrieval (IR) and retrieval-augmented generation (RAG) as important natural language processing (NLP) tasks for efficiently obtaining relevant information from vast datasets. RAG combines IR with generative capabilities, providing contextually appropriate and factual responses to users’ questions. The chapter explains key concepts such as cosine similarity and embeddings, which facilitate nuanced retrieval processes. The chapter presents a practical Python example implementing a simple IR and RAG system, providing guidance for design decisions such as chunk size, model selection, and query crafting. -
11. Perspectives on LLMs in Management and Qualitative Research
- Open Access
PDF-Version jetzt herunterladenAbstractThis chapter explores the evolving role of large language models (LLMs) in management and qualitative research, considering their transformative impact on research. It discusses the transition from basic text analysis tools to sophisticated analytical assistants, propelled by advancements in multimodal models, reasoning models, and agentic AI. Future developments are envisioned, such as LLMs processing various data formats and supporting complex reasoning tasks, enabling researchers to automate labor-intensive workflows. The chapter concludes by encouraging researchers to critically engage with AI technologies, striking a balance between the benefits of AI-driven insights and the need to mitigate their limitations.
-
- Titel
- AI for Qualitative Research
- Verfasst von
-
Diana Garcia Quevedo
Josue Kuri
- Copyright-Jahr
- 2026
- Verlag
- Springer Nature Switzerland
- Electronic ISBN
- 978-3-032-08872-7
- Print ISBN
- 978-3-032-08871-0
- DOI
- https://doi.org/10.1007/978-3-032-08872-7
Die PDF-Dateien dieses Buches wurden gemäß dem PDF/UA-1-Standard erstellt, um die Barrierefreiheit zu verbessern. Dazu gehören Bildschirmlesegeräte, beschriebene nicht-textuelle Inhalte (Bilder, Grafiken), Lesezeichen für eine einfache Navigation, tastaturfreundliche Links und Formulare sowie durchsuchbarer und auswählbarer Text. Wir sind uns der Bedeutung von Barrierefreiheit bewusst und freuen uns über Anfragen zur Barrierefreiheit unserer Produkte. Bei Fragen oder Bedarf an Barrierefreiheit kontaktieren Sie uns bitte unter accessibilitysupport@springernature.com.
