A report looking at a system to extract themes from public consultations highlights human and LLM-based checks.

One of the largest insurance companies in the U.S. handles 12,000 policy requests every day. Two years back, their call center had 180 agents who answered simpl ...

This approach combined: (1) supervised machine learning for text classification, (2) comparative topic modeling with both theory-driven and data-driven Latent Dirichlet Allocation (LDA) to identify ...