The Civic Commons Access to tools for building community where you live
Recipe · from the prosocial design collection

Suggest Constructive Rephrased Messages

Use a large language model to offer users rephrased comments to encourage constructive conversations.

Suggest Constructive Rephrased Messages

Goal: Improve conversations on divisive topics Evidence rating (PDN): Tentative Civic signal: Understand — Promote thoughtful conversation When to use: Interactive

What it is

Use a large language model to offer users rephrased comments to encourage constructive conversations.

Intended impact

To improve the civility of discussions.

Evidence that it works

Argyle et al. (2023) conducted an online experiment where pairs of participants discussed controversial topics. Some of the participants had access to an AI assistant that suggested rephrasing comments to either 1) restate the message of their conversational dialogue, implying understanding; 2) validate the other participant’s perspective; or 3) make the message more polite. Access to such an AI-assistant significantly improved their conversation partner’s reported conversation quality, and decreased a divisiveness metric created by the authors. Effect sizes estimated conservatively are in the 2.5-5% range. It is important to note that it is unclear whether these results would generalize to scenarios where knowledge about these AI-tools (and that people are using them online) is widespread -- especially since participants in the “receiving” end (i.e., whose conversational partner had access to the chat bot), were not aware of it; and since the study never considered the case in which both participants had access to the AI assistant.

Why it matters

Improving the quality of online conversation on divisive topics can help decrease polarization and increase the well-being of users.

Special considerations

Examples

This intervention entry currently lacks photographic evidence (screencaps, &c.)

Citations

  • *AI Chat Assistants can Improve Conversations about Divisive Topics* — Lisa P. Argyle, E. Busby, J. Gubler, C. Bail, Thomas Howe, C. Rytting, D. Wingate (ArXiV, February 14, 2023). https://doi.org/10.48550/arXiv.2302.07268

---

From the Prosocial Design Network's Digital Intervention Library (https://www.prosocialdesign.org/library/suggest-constructive-rephrased-messages), licensed CC BY-SA 4.0. Reformatted for the RT Commons; text otherwise as published. Library citation: Prosocial Design Network (2024), Digital Intervention Library, https://doi.org/10.17605/OSF.IO/Q4RMB. Anything built from this pattern should credit the Prosocial Design Network and the researchers cited above.

Details

  • goal: Improve conversations on divisive topics
  • citations: [object Object]
  • image alt: An illustration of the pop-up rephrasing prompt window.
  • image url: https://cdn.prod.website-files.com/647f696dc653a97c26f42a0b/64c3ee6673e82049f9bdf01e_230628_ai-assistant%404x.png
  • pdn rating: Tentative
  • when to use: Interactive
  • civic signal: Understand
  • pdn library doi: 10.17605/OSF.IO/Q4RMB
  • civic signal goal: Promote thoughtful conversation
Related by topic

Contributed by Prosocial Design Network · prosocialdesign.org · CC BY-SA 4.0

Original source: https://www.prosocialdesign.org/library/suggest-constructive-rephrased-messages

See something to fix or add? Suggest an edit on GitHub — the commons lives in git too, and its history is the changelog.

prosocial-designdesign patternpdn-rating:tentativewhen:interactivecivic-signal:understandpromote thoughtful conversation

Remix this in Relational Builder  Browse the commons