Papers with inductive coding

3 papers
Text Annotation via Inductive Coding: Comparing Human Experts to LLMs in Qualitative Data Analysis (2025.findings-naacl)

Copied to clipboard

Challenge: Qualitative data analysis (QDA) is an important research method across fields such as marketing, media studies, social science, psychology, medical research, and others.
Approach: They evaluate the performance of open-source LLMs by comparing them to human experts.
Outcome: The proposed method is based on inductive coding using large language models.
Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors (2026.findings-acl)

Copied to clipboard

Challenge: Firearm violence research remains underfunded and difficult to scale due to the lack of funding from the NIH and CDC.
Approach: They use open-source large language models to inductively code interviews with 21 Black men who have survived community firearm violence.
Outcome: The use of open-source LLMs to inductively code interviews with 21 Black men shows that the models can identify important codes, but that they are highly sensitive to data processing.
A Computational Method for Measuring Open Codes in Qualitative Analysis (2026.findings-acl)

Copied to clipboard

Challenge: Qualitative analysis is widely adopted across many social science disciplines.
Approach: They propose a theory-informed computational method for measuring inductive coding results from humans and GAI.
Outcome: The proposed method captures breadth, consensus, unique contribution, and systematic deviation without assuming ground truth.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations