Modeling Professionalism in Expert Questioning through Linguistic Differentiation

TL;DR

This paper develops a linguistic framework to model and evaluate professionalism in expert questioning, demonstrating that professionalism can be quantified and distinguished using interpretable linguistic features across domains.

Contribution

It introduces a novel annotation framework and demonstrates that linguistic features can effectively model professionalism in expert questions, outperforming baseline classifiers.

Findings

Linguistic features correlate with perceived professionalism and question origin.

A classifier trained on these features surpasses baseline models in identifying expert questions.

Professionalism is a learnable, domain-general construct captured through linguistic analysis.

Abstract

Professionalism is a crucial yet underexplored dimension of expert communication, particularly in high-stakes domains like finance. This paper investigates how linguistic features can be leveraged to model and evaluate professionalism in expert questioning. We introduce a novel annotation framework to quantify structural and pragmatic elements in financial analyst questions, such as discourse regulators, prefaces, and request types. Using both human-authored and large language model (LLM)-generated questions, we construct two datasets: one annotated for perceived professionalism and one labeled by question origin. We show that the same linguistic features correlate strongly with both human judgments and authorship origin, suggesting a shared stylistic foundation. Furthermore, a classifier trained solely on these interpretable features outperforms gemini-2.0 and SVM baselines in distinguishing expert-authored questions. Our findings demonstrate that professionalism is a learnable, domain-general construct that can be captured through linguistically grounded modeling.