---
title: "Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.11749v1"
permalink: "https://feed.astralor.com/items/itm_d8d9cfc47d1808c58edcea9a"
published: "2026-07-13T16:06:23.000Z"
score: 78
channel: "ai"
tags: ["GPT-5","Large Language Models","Sentiment Analysis","Field Experiment","Workplace Communication"]
---

# Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement

## AI commentary

> What I find most compelling about this paper is that it uses a rigorous field experiment to answer a practical yet often overlooked question: does AI rewriting emails actually work? The result is surprising—AI editing doesn't directly boost reply rates but indirectly influences behavior through tone. For enterprises, this means deploying AI writing tools should focus on emotional orientation, not just efficiency metrics. For scholars of human-AI interaction, this experimental design is worth learning from.

## At a glance

This randomized crossover field experiment investigates how AI-assisted writing affects recipient behavior in workplace emails. 121 employees sent 16,880 emails over three weeks under conditions of unaided writing, GPT-5 playful rewrite, and GPT-5 professional rewrite. Playful editing increased emotional positivity, while professional editing decreased it, yet neither directly altered open rates, reply rates, or response times. However, within-sender positivity strongly predicted opening and replying, revealing an indirect pathway through which AI editing shapes workplace engagement via the emotional tone of language.

## Key points

- 121 employees from 6 companies sent 16,880 emails across three writing conditions. 
- Playful tone significantly increased emotional positivity (B=+0.068), while professional tone decreased it (B=-0.041).
- AI editing had no direct effect on open rates, reply rates, or response times, but sender positivity strongly predicted behavior (open OR=2.05, reply OR=3.32).
- Conclusion: AI shapes workplace engagement indirectly through emotional tone rather than direct use.

## Full text

Large language models (LLMs) are rapidly reshaping workplace communication, yet whether AI-assisted writing changes how recipients actually behave, and through what channel, remains unknown. Here, in a randomized crossover field experiment, 121 employees across six companies sent work emails under three conditions over three weeks: unaided writing, GPT-5 rewriting in a playful tone, and GPT-5 rewriting in a professional tone. Across 16,880 emails, playful editing increased emotional positivity (B=+0.068, p<0.001), and professional editing decreased it (B=-0.041, p<0.001), yet neither condition directly altered open rates, reply rates, or response times. Instead, within-sender positivity strongly predicted both opening (OR=2.05) and replying (OR=3.32, p<0.001), a significant indirect pathway through which AI editing shaped behavior, in the absence of any direct effect. These findings suggest that AI-assisted communication shapes workplace engagement not through its use, but through the emotional tone of the language it produces.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_d8d9cfc47d1808c58edcea9a