Saved in:
Bibliographic Details
Main Author: Zupic, Ivan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19271
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918398810652672
author Zupic, Ivan
author_facet Zupic, Ivan
contents While many researchers use Large Language Models (LLMs) through chat-based access, their real potential lies in leveraging LLMs via application programming interfaces (APIs). This paper conceptualizes LLMs as universal text processing machines and presents a comprehensive workflow for employing LLMs in three qualitative and quantitative content analysis tasks: (1) annotation (an umbrella term for qualitative coding, labeling and text classification), (2) summarization, and (3) information extraction. The workflow is explicitly human-centered. Researchers design, supervise, and validate each stage of the LLM process to ensure rigor and transparency. Our approach synthesizes insights from extensive methodological literature across multiple disciplines: political science, sociology, computer science, psychology, and management. We outline validation procedures and best practices to address key limitations of LLMs, such as their black-box nature, prompt sensitivity, and tendency to hallucinate. To facilitate practical implementation, we provide supplementary materials, including a prompt library and Python code in Jupyter Notebook format, accompanied by detailed usage instructions.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19271
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Human-Centered Workflow for Using Large Language Models in Content Analysis
Zupic, Ivan
Computation and Language
Artificial Intelligence
While many researchers use Large Language Models (LLMs) through chat-based access, their real potential lies in leveraging LLMs via application programming interfaces (APIs). This paper conceptualizes LLMs as universal text processing machines and presents a comprehensive workflow for employing LLMs in three qualitative and quantitative content analysis tasks: (1) annotation (an umbrella term for qualitative coding, labeling and text classification), (2) summarization, and (3) information extraction. The workflow is explicitly human-centered. Researchers design, supervise, and validate each stage of the LLM process to ensure rigor and transparency. Our approach synthesizes insights from extensive methodological literature across multiple disciplines: political science, sociology, computer science, psychology, and management. We outline validation procedures and best practices to address key limitations of LLMs, such as their black-box nature, prompt sensitivity, and tendency to hallucinate. To facilitate practical implementation, we provide supplementary materials, including a prompt library and Python code in Jupyter Notebook format, accompanied by detailed usage instructions.
title A Human-Centered Workflow for Using Large Language Models in Content Analysis
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.19271