Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

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

Source

arXiv

arxiv.org/abs/2607.11749v1

Read the source

Source

Plain-Language Brief

A study found that using a large language model (GPT-5) to write work emails in a playful tone increased emotional positivity in recipients, while using a professional tone decreased it. However, neither condition directly affected open rates, reply rates, or response times. The study suggests that the emotional tone of AI-generated language may indirectly influence behavior through its impact on the sender's emotional state.

What the Document Says

  • The study involved 121 employees from six companies who 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, the playful editing increased emotional positivity (B=+0.068, p<0.001), while professional editing decreased it (B=-0.041, p<0.001).
  • Neither condition directly altered open rates, reply rates, or response times.
  • Within-sender positivity strongly predicted both opening and replying (OR=2.05 for opening, OR=3.32 for replying, p<0.001)
  • There was a significant indirect pathway through which AI editing shaped behavior, in the absence of any direct effect.

Key Concepts Mentioned

  • Large language models
  • GPT-5
  • work emails
  • emotional positivity
  • open rates
  • reply rates
  • response times

Claims Made by the Document

  • Playful editing increases emotional positivity in recipients.
  • Professional editing decreases emotional positivity in recipients.
  • Neither playful nor professional editing directly affects open rates, reply rates, or response times.

Evidence Used

  • Increase in emotional positivity for playful editing (B=+0.068, p<0.001).
  • Decrease in emotional positivity for professional editing (B=-0.041, p<0.001).
  • No significant effect on open rates, reply rates, or response times.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.