@bennokrojer.bsky.social didn't your lab have something like this happen

such a valuable resource! thanks for sharing

wow. you always hear these horror stories (eg spelling the university/prof name wrong, or worse, writing the wrong name altogether) and think itll never happen to you but this is a great reminder that nobody is immune. hopefully your typos weren't so bad!

oh my 😅 hope you're not speaking from your own experience

inspired by having to re-upload my arxiv submission 3!!! times tonight

and once you correct that typo, proofread again and find nothing else, and re-submit, only then does a SECOND typo suddenly emerge 😭

Forgot to attach this screenshot from our discussion in the reply

We definitely think the platform / setting would strongly influence this (especially online vs in person & if online, how it’s moderated)!

Yes! While this work focused on in-person small-group facilitated conversations, they did range from more discussions on community topics as well as conversation games and policy deliberations. The biggest factors were purpose (eg game vs story sharing vs deliberation) as well as facilitator style

This work was done with awesome collaborators Maggie Hughes, Brandon Roy, Deb Roy, and @jad-kabbara.bsky.social from @mit.edu @medialab.bsky.social

Make sure to check out Brandon’s presentation on Friday Nov 7, Room A109 at 10:30!

Paper link: ​​https://aclanthology.org/2025.emnlp-main.1798/

8/8

Overall, responsivity offers a structural lens on how dialogue unfolds 🧱,

laying groundwork for understanding what makes conversations constructive, collaborative, and engaging across contexts 🌱🫂

Future work: richer metrics + applications in civic 🗳️ + online spaces 🌍

7/

When applied across diverse facilitated discussions, our metrics reveal 🔎

5 distinct, interpretable 🧠 conversation types aligned with their intended purposes 🎯 + facilitation styles 📣

6/

Using these annotations, we derive conversation-level metrics capturing:

• Balance b/t speakers ⚖️
• Turn sequence variability 🔁
• Who responds to whom 🙋‍♀️↔️👂
• Distribution of substantive responses 📊
• Facilitator-participant dynamics 🧩

5/

To operationalize responsivity at scale, we leverage LLMs and find:

• LLM 🤖 annotations align 🤝 more closely with human 👥 judgments than a semantic similarity baseline
• Humans themselves vary, reflecting task subtlety of the task 🤔

4/

We further distinguish between mechanical and substantive responsivity:

• *Substantive* responses meaningfully engage 💡, connect 🔗, and build 🌱
• *Mechanical* responses maintain flow 🌀w/o offering new substantial content (e.g., conversational hand-offs, social cues…)

3/

Most NLP work on discourse focuses on toxicity 🚩or polarization ⚠️.

But constructive dialogue is grounded in something more foundational:

*Responsivity* — the degree to which participants listen 👂 and respond 🗣️to one another.

2/

This paper underscores how “misinformation” is not easily operationalized as single pieces of factually untrue content, but often takes shape through the motivated amplification of specific evidence (often true evidence) that serves to build and reinforce misleading frames.

Also grateful for this hobby that allows me to feel connected to my hands, creativity, and family (esp my grandma). There is joy in the process of creating slowly