4 papers
Dimensionality in Satisfaction Ratings
Andrew Hong, Jason Potteiger
We used a large language model (GPT-4.1) to annotate the text of about 9,000 support conversations at a global consumer-goods firm, decomposing customer-care satisfaction into comp…
What sentiment analysis can't see: Measuring whether customers were helped, and what went wrong, across 70,000 support conversations
Jason Potteiger
Most companies read their customer support data at scale using sentiment analysis, which measures how customers sound rather than whether they were satisfied with the result. We te…
The signal is the ceiling: Measurement limits of LLM-predicted experience ratings from open-ended survey text
Andrew Hong, Jason Potteiger, Luis E. Zapata
An earlier paper (Hong, Potteiger, and Zapata 2026) established that an unoptimized GPT 4.1 prompt predicts fan-reported experience ratings within one point 67% of the time from op…
LLM Predictive Scoring and Validation: Inferring Experience Ratings from Unstructured Text
Jason Potteiger, Andrew Hong, Ito Zapata
We tasked GPT-4.1 to read what baseball fans wrote about their game-day experience and predict the overall experience rating each fan gave on a 0-10 survey scale. The model receive…