Dimensionality in Satisfaction Ratings
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.
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
Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability
This paper presents a scalable framework using LLMs for implicit sentiment analysis of product desirability from qualitative feedback, achieving up to 0.97 Pearson correlation and 94% accuracy while providing explanations, with GPT-4o-mini offering similar performance at 94% lower cost.
A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis
This paper presents a spectral phase diagram for binary few-shot classification, analyzing intrinsic dimensionality and geometric saturation for representational diagnosis.
Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies
This paper presents a zero-shot evaluation of three LLMs (Claude, GPT-5.4, Gemini) on a 13-class emotion classification task, finding no model exceeds 39.9% accuracy and revealing systematic failures on specific emotions such as love, confusion, and shame.
Using GPT-4 to deliver a new customer service standard
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.
The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis
This paper presents methods for SemEval-2026 Task 3, using transformer ensembles and LLM-generated annotations to predict continuous valence and arousal scores in dimensional aspect-based sentiment analysis.