Amazing to finally see this published, congratulations man!

Thanks!! Please do reach out if you’d like help — the survey instrument and model code are in the replication package, but I’m happy to help you get set up!

Lmk if you’d like to give it a try yourself!

6/ reach out if you’d like to try using the WWYS method yourself! I can set you up with the survey instrument and model code. I’m also looking for collaborators to apply in different languages/country settings!

5/ and I also derive causal estimates of self-censorship by analyzing treatment effects on a second “outspokenness” dimension generated by my Wordsticks model (details in paper)

4/ by manipulating the social context in the WWYS question in a between-subjects experiment, I derive causal estimates of ideological “code-switching” caused by liberal and conservative interlocutors (using close-friend speech as a reference/control)

3/ I scale the data using a model similar to Wordfish (but since it’s for ordinal data, I call it WordSTICKS): the ideological content of each phrase is defined by the latent ideal points of the people who use/avoid the phrase

2/ I collect data using the “What Would You Say?” (WWYS) question, which asks respondents whether they would use various politically-charged words and phrases in a given social context (like a conversation with a close friend)

And huge thanks to the #JEPS editors and our anonymous reviewers, who saw the value in a paper that was in-between a “software” and “research” contribution, gave us spot-on feedback throughout (even testing ReChat themselves!), and supported us to write the paper we really wanted to write!

Thanks Jason! That’s so great to hear after the long journey to get here — credit goes to @xiaoxiaoshen.bsky.social for recognizing the need and taking the entrepreneurial steps to make the idea a reality!

Thanks Joris! We designed it to be accessible to anyone who can run a survey, in the hope of making chats an accessible research design component for more scholars. We’re keen to work directly with early adopters, so please reach out if you’re interested in trying it out!

Amazing! Would love to help get you started - we have instructional materials on reso.chat and in the paper itself, but we’re keen to work directly with early-adopters! We’re also potentially open to new feature requests…

Also, big thanks to @ylelkes.bsky.social @feedkoko.bsky.social and @alvinyxz.bsky.social for sharing their experiences with chat studies that helped guide our decisions from early on in this project!

… and see how to use the r package we provide to process chat transcripts and merge them to survey data github.com/willschulz/r...

You can even use our replication code to explore chat analyses... doi.org/10.7910/DVN/...

📚 … And read our paper (cup.org/4gFUahQ) where we:
- Demo ReChat in a pair of studies on co-partisan chats
- Assess how chat samples differ from typical survey samples due to self-selection
- Show that strong ideologues say more in political chats (just like on social media)

🚀 Want to get started?
If you want to give ReChat a try, reach out to us! We want to help you do research with ReChat 🤝🧑‍💻You can also sign up at reso.chat/signup –– ReChat is accessible to all academics on a pay-what-you-can donation basis 💸

Ever wanted to run a study with real-time, live text conversations?
ReChat lets you embed a live chat right in your Qualtrics survey, without writing any code. Perfect for focus groups, deliberation, or taking your survey experiment to the next level by using social interaction as the IV or DV! 🙌