When LLMs fall short in Deductive Coding: Model Comparison and Human AI Collaboration Workflow Design

Abstract

With generative artificial intelligence driving the growth of dialogic data in education, automated coding is a promising direction for learning analytics to improve efficiency. This surge highlights the need to understand the nuances of student-AI interactions, especially those rare yet crucial. However, automated coding may struggle to capture these rare codes due to imbalanced data, while human coding remains time-consuming and labour-intensive. The current study examined the potential of large language models (LLMs) to approximate or replace humans in deductive, theory-driven coding, while also exploring how human-AI collaboration might support such coding tasks at scale. We compared the coding performance of small transformer classifiers (e.g., BERT) and LLMs in two datasets, with particular attention to imbalanced head-tail distributions in dialogue codes. Our results showed that LLMs did not outperform BERT-based models and exhibited systematic errors and biases in deductive coding tasks. We designed and evaluated a human-AI collaborative workflow that improved coding efficiency while maintaining coding reliability. Our findings reveal both the limitations of LLMs -- especially their difficulties with semantic similarity and theoretical interpretations and the indispensable role of human judgment -- while demonstrating the practical promise of human-AI collaborative workflows for coding.