TopicENA: Enabling Epistemic Network Analysis at Scale through Automated Topic-Based Coding

TopicENA is a new framework that combines BERTopic with Epistemic Network Analysis to automatically analyze concept relationships in large text datasets without manual coding. The research demonstrates that automated topic modeling can replace expert manual coding while maintaining analytical quality, making network analysis scalable for large corpora.

• →TopicENA merges BERTopic with Epistemic Network Analysis to automate concept coding in text analysis.
• →Coarse-grained topics work better for large datasets while fine-grained topics are more effective for smaller datasets.
• →Topic inclusion thresholds should be adjusted based on quality indicators to balance network consistency and interpretability.
• →The framework successfully scales to substantially larger datasets than previous ENA studies.
• →TopicENA eliminates the scalability bottleneck of manual expert coding in traditional epistemic network analysis.