Dimensionality in Satisfaction Ratings

arXiv cs.CL Papers

Summary

This paper uses GPT-4.1 to annotate 9,000 support conversations and decompose customer satisfaction into component axes, validating the annotations against self-reported ratings and revealing lower satisfaction in full-census data compared to survey responses.

arXiv:2607.11026v1 Announce Type: new Abstract: 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 component axes (overall, agent, outcome, product, and customer effort), and validated the LLM annotations against the satisfaction ratings customers gave themselves. Four of five axes track self-reported satisfaction closely (overall, agent, and outcome near an unadjusted 0.65; effort -0.54), while product satisfaction is weak against the available proxy. The unadjusted correlation also understates the alignment: the disagreements concentrate in a small, readable tail of divergent sessions rather than in general drift, and the overall correlation rises to 0.811 when only the severe divergences are excluded and to 0.914 when the full divergent tail is excluded. The axes are also highly collinear, and adding them to the overall score does not improve prediction of the customer's rating, the decomposition's value is not incremental prediction but attribution and coverage. And, with greater coverage the picture of the data changes. Read on every contact rather than the few that return a survey, satisfaction is markedly lower than the survey reports (a full-census 2.91 against the surveyed 3.62 on a five-point scale). The promise of decomposed satisfaction as a methodology is the ability to identify more nuanced drivers of customer experience in conversational data.
Original Article
View Cached Full Text

Cached at: 07/14/26, 04:23 AM

# Dimensionality in Satisfaction Ratings
Source: [https://arxiv.org/abs/2607.11026](https://arxiv.org/abs/2607.11026)
[View PDF](https://arxiv.org/pdf/2607.11026)

> Abstract: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 component axes \(overall, agent, outcome, product, and customer effort\), and validated the LLM annotations against the satisfaction ratings customers gave themselves\. Four of five axes track self\-reported satisfaction closely \(overall, agent, and outcome near an unadjusted 0\.65; effort \-0\.54\), while product satisfaction is weak against the available proxy\. The unadjusted correlation also understates the alignment: the disagreements concentrate in a small, readable tail of divergent sessions rather than in general drift, and the overall correlation rises to 0\.811 when only the severe divergences are excluded and to 0\.914 when the full divergent tail is excluded\. The axes are also highly collinear, and adding them to the overall score does not improve prediction of the customer's rating, the decomposition's value is not incremental prediction but attribution and coverage\. And, with greater coverage the picture of the data changes\. Read on every contact rather than the few that return a survey, satisfaction is markedly lower than the survey reports \(a full\-census 2\.91 against the surveyed 3\.62 on a five\-point scale\)\. The promise of decomposed satisfaction as a methodology is the ability to identify more nuanced drivers of customer experience in conversational data\.

## Submission history

From: Jason Potteiger \[[view email](https://arxiv.org/show-email/e3615406/2607.11026)\] **\[v1\]**Mon, 13 Jul 2026 02:45:35 UTC \(1,040 KB\)

Similar Articles

Using GPT-4 to deliver a new customer service standard

OpenAI Blog

Ada uses GPT-4 and a multi-agent system powered by OpenAI's API to improve customer service quality, doubling resolution rates from 30% to 60-80% while maintaining high containment rates, establishing a new industry standard beyond traditional metrics.