Kobin Kendrick

I'll add more features over time, like better line type classification, customizable styles, and a downloadable version that runs locally.

What features would you most like to see?

I developed it with Claude and didn't write a single line of code. I just described the features the app should have and Claude worked his magic. This is just one example of how AI can support CA research. #AIforCA

I've developed a simple app to help with transcription: Ript. It solves three problems: finding symbols, numbering lines, and styling multimodal transcripts.

App: ript-editor.vercel.app
Guide: docs.google.com/document/d/1...

YouTube video by Kobin Kendrick CA methods: Making video clips with LosslessCut

This is an excellent app (with an ugly icon). I made a short video on how to use it: youtu.be/_iVbBpAqRa8?...

Spread the word! The next York Conference on Conversation Analysis will be held 17-18 July. Encourage your MA/PhD students to submit an abstract. Deadline: 10 April.

In addition to presenting their research, Ana Cristina Ostermann and Richard Ogden will also deliver post-conference workshops!

After lunch break now and @luyang-zhou.bsky.social is presenting on Children’s Self-Selection in Pediatric Consultations in China #CAday2025

Great to see this write-up of @luyang-zhou.bsky.social’s PhD research. It promises to make an important and novel contribution to the study of turn-taking and overlap management, as well as paediatric medical interactions in China.

We’re lucky to have Richard at YorCCA 2026! In addition to his talk, he’ll also offer a post-conference workshop. Stay tuned for details!

Find out more about YorCCA:
sites.google.com/york.ac.uk/y...

I’m very excited for the next YorCCA! Spread the word to your MA and PhD students.

We have a CA pathway in our MA Applied Linguistics at York. Includes dedicated modules on CA, multimodality, and institutional interaction (taught by Merran Toerien). Applications open for 26-27.

Find out more
www.york.ac.uk/study/postgr...

Well that didn't take long. Gemini 3 Pro and Claude 4.5 Opus can both recognize underlined text and re-transcribe CA transcripts from screenshots. Gemini is more accurate but still makes some mistakes. I gave them a transcript from Clayman (2013) with lots of complex overlap as a test.

The prompt was pretty basic:

“Could you please create an annotated infographic, using the attached screenshot of a transcript from a news interview? The infographic should present details from a conversation-analytic study of the interview based on research by Steve Clayman and John Heritage.”

We've now entered the era of AI-generated infographics. I asked Gemini to analyse a screenshot of a data extract from Clayman (2013) and to create an infographic. This is what it came up with.

#YorCCA What is YorCCA? The York Conference on Conversation Analysis (YorCCA) is a CA conference organised by PhD researchers at the University of York and affiliated with the Centre for Advanced Studies in L...

🎉 Great news! YorCCA 2026 will take place on 17–18 July 2026 at the University of York.

📅Key Dates
• Main Conference: 17 July 2026
• Workshops: 18 July 2026

🌐Further details will be available on our official channels shortly. Mark your calendars!
sites.google.com/york.ac.uk/y...

TIL: AI models can't see underlined text. ChatGPT 5.1 Thinking, Claude Sonnet 4.5 and Gemini 2.5 Pro all struggle to recognize which letters are underlined. This is my new test for AGI.

What we’re not drowning in is money. It’d be great to hire students and post-docs for projects, but in the absence of that, I’ll gladly use tools that allow me to do more with less. I don’t see this as unethical.

There are interactional phenomena that are relatively rare or elusive yet analytically significant. Gene Lerner’s approach is to build collections of these over years or decades as one comes across specimens. An AI that can watch and listen might find hundreds of these in days or weeks.

I’d say we’re well on our way to artificial general intelligence (AGI), systems that are as intelligent as humans across all domains, including CA. The real breakthrough will be when AIs can analyze video data directly and help us build and analyze collections.

Post-decline requesting and the reversal of refusals A research proposal Post-decline requesting and the reversal of refusals: A research proposal Claude Sonnet 4.5 with Kobin H. Kendrick Introduction This report presents a research proposal grounded in an empirical observ...

I gave Claude Sonnet 4.5 a transcript I use for teaching CA and asked it to develop a research proposal based on an observation about the data. Its observation was original, insightful, and analytically significant. This is wild.

docs.google.com/document/d/1...

AI models are good at literature reviews. What I like about this test is that coming up with a good idea for a project, or even a good place to start, is a harder task.

Projecting the Next Move: Embodied Action Projection in Collaborative Physical Tasks (Sonnet 4.5).md Projecting the Next Move: Embodied Action Projection in Collaborative Physical Tasks Claude Sonnet 4.5 Core Research Question How do participants use embodied conduct (gaze, gesture, body orientation,...

Whenever a new AI model is released, I ask it to propose a PhD project in CA. Today Anthropic released Claude Sonnet 4.5, and its proposal is my favourite so far. If anyone, human or machine, would like to do this project, I'd gladly supervise it.

docs.google.com/document/d/1...

The YorCCA 2025 Report is out in the latest ISCA newsletter!

www.conversationanalysis.org/yorcca-2025-...

A huge thank you to all presenters & participants. We look forward to seeing you at YorCCA 2026!

Very excited to announce this faculty search at Rutgers! Looking for a wonderful new colleague to join us in Communication #EMCA #LSI @ica-lsi.bsky.social @lansi2024.bsky.social
jobs.rutgers.edu/postings/258...

I asked ChatGPT o3 to replicate the findings of Pomerantz (1984). I gave it a summary and a set of 10 transcripts (NB).

Results were mixed: the evidence it presented was clear in some cases, but less so in others, and some observations were superficial.

drive.google.com/file/d/1l4rM...

As a lecturer, I tend to size up AIs by academic level, from undergrad to PhD candidate. Where would you place these AIs on that scale?

These observations are not entirely dissimilar from some early-stage CA projects: spotting a "media disclaimer" in the data could very well serve as a point of departure for further analysis. It's not an uninteresting observation.

The phenomena the models found (e.g. “weather talk”) lack the fine-grained specificity CA generally demands, but they did identify multiple instances of "a something". Questions about and assessments of the weather are indeed recurrent in the NB calls, for example.

Projected co-presence (Opus) Projected co-presence work Claude Opus Introduction This report identifies a previously undocumented interactional phenomenon in telephone conversation: projected co-presence work. This refers to the...

Projected co-presence work by Claude Opus 4

Opus identified “projected co-presence work” as a phenomenon in which callers negotiate future face-to-face meetings and manage relational and practical dimensions of reunion.

docs.google.com/document/d/1...

Media distancing disclaimers (o3) Media distancing disclaimers ChatGPT o3 Introduction Recent re‑examination of the NB telephone corpus reveals a recurrent practice in which speakers profess a categorical refusal to watch television...

Media distancing disclaimers by ChatGPT o3

o3 identified “media-distancing disclaimers” as a recurrent move: speakers emphatically refuse to watch distressing TV coverage to project moral self-care, recruit affiliation, and pivot out of sequences of shared lament.

docs.google.com/document/d/1...

Weather talk (o3) Weather talk ChatGPT o3 The nine telephone calls from the NB collection display a striking regularity: the first fully‑fledged topic after the canonical opening sequence is almost always an assessm...

Weather talk by ChatGPT o3

o3 identified “weather talk” as a systematic practice: immediately after greetings, callers offer stance-laden weather assessments (e.g. “beautiful,” “lousy”) to secure affiliation and signal the shift into substantive conversation.

docs.google.com/document/d/1...