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

2026-07-13

AI Summary

This study investigates how the tone of AI-assisted work emails influences recipient behavior. Through a randomized crossover field experiment, we leveraged GPT-5 to rewrite employee emails in either playful or professional tones and combined large-scale A/B testing with causal inference to assess impacts on open rates, reply rates, and response times. Results indicate that AI editing per se does not directly alter behavior but indirectly enhances engagement by modulating emotional tone: playful phrasing significantly increased message positivity (B = +0.068), whereas professional phrasing reduced it (B = −0.041). Moreover, greater message positivity strongly predicted higher odds of both opening (OR = 2.05) and replying (OR = 3.32). This work provides the first empirical evidence that the effectiveness of AI-mediated communication hinges on linguistic emotionality rather than mere technological intervention.

Abstract

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.

Problem

• AI-assisted writing
• workplace communication
• emotional tone
• recipient engagement
• large language models

Innovation

• playful AI
• emotional tone
• indirect effect
• field experiment
• LLM-assisted writing