







Maite Taboada
Maite Taboada. Professor. Department of Linguistics, Simon Fraser University. Research: discourse analysis, computational linguistics
The Discourse Encouragement Fund
News about about the next-generation open source Discourse forum software.

Building a Discourse Community
Sure, anyone can set up their very own Discourse in 30 minutes or less. But how do you get people to go there?

Building a Discourse Community
Sure, anyone can set up their very own Discourse in 30 minutes or less. But how do you get people to go there?

Toward Automated Discourse Network Analysis
Discourse Network Analysis has long been capped by the price of expert judgment. Here is a design for automating it at corpus scale without surrendering command of meaning — and FineStructure, the open-source workbench I am building for it.

The Universal Rules of Civilized Discourse
With Discourse, it was clear that we needed to totally reboot the software to create next-generation forum software. But code is only part of the story. Any reasonable attempt at delivering a Civilized Discourse Construction Kit has to provide a safe, simple default set of guidelines for civilized discourse.

Discourse and the Fediverse!
The Fediverse offers ways to expand the reach of Discourse communities and help them build bridges with people active in other spaces, all while keeping the conversation civil, meaningful and focused.

Using Discourse instead of an email mailing list
🔖 This topic explains the advantages of using Discourse over traditional email mailing lists for group conversations and community management. 🙋 Required user level: All users Discourse is a modern platform designed for group conversations that offers significant advantages over traditional email mailing lists. While email remains effective for one-on-one or small group communications, Discourse excels at handling larger, ongoing discussions. Here’s why you shoul...

Home – The Discourse.
The Discourse provides community-powered journalism in Cowichan Valley, Nanaimo and Comox Valley. We are here to listen to you and respond with in-depth news about the issues you care about.

Do LLMs write like humans? Variation in grammatical and rhetorical styles
As large language models (LLMs) have grown in power and become more widely available, research has focused on their ability to complete various tasks and the biases they exhibit when doing so. In this study, we instead examine their writing style in detail. We show that instruction-tuned models, which are trained to answer questions and solve problems, have a distinct noun-heavy, informationally dense writing style, even when prompted to match the style of informal speech and writing. These findings suggest that instruction-tuned models generate text that does not align with genre conventions familiar to human audiences, and demonstrate the value of linguistic variables in evaluating the output of LLMs., Large language models (LLMs) are capable of writing grammatical text that follows instructions, answers questions, and solves problems. As they have advanced, it has become difficult to distinguish their output from human-written text. While past research has found some differences in features such as word choice and punctuation and developed classifiers to detect LLM output, none has studied the rhetorical styles of LLMs. Using several variants of Llama 3 and GPT-4o, we construct two parallel corpora of human- and LLM-written texts from common prompts. Using Douglas Biber’s set of lexical, grammatical, and rhetorical features, we identify systematic differences between LLMs and humans and between different LLMs. These differences persist when moving from smaller models to larger ones and are larger for instruction-tuned models than base models. This observation of differences demonstrates that despite their advanced abilities, LLMs struggle to match human stylistic variation. Attention to more advanced linguistic features can hence detect patterns in their behavior not previously recognized.

Getting started - Docs
Discourse Graphs are a tool and ecosystem for collaborative knowledge synthesis, enabling researchers to map ideas and arguments in a modular, composable graph format.
Proposal: a community lexicon for standalone images
discourse.atmosphere.communityluminframe.com
made in the Atmosphere in luminframe.com
Discourse Graphs
@discoursegraphs.bsky.social
Discourse Graphs are an information model that enables everyone to map their ideas and arguments in a modular, composable graph format. discoursegraphs.com
Full essay below. Written at @bmann.ca 's prompting in the Discourse thread — language barriers keeping atproto's non-English implementations out of the design conversation. night-terrace.offprint.app/a/3mlxygoehwd23-three-layers-…
Three Layers of Post Editing in atproto: A Case for History-Preserving Design | Nighthaven⛺︎ | Offprint
night-terrace.offprint.appHey @alexbenzer.com, we're having a discussion on the Discourse that could use your input. #atproto
A lexicon for game activity sharing
discourse.atmosphere.communityNanoarguments
Did you know Reams supports @discoursegraphs.bsky.social? We have the plugin enabled in the Obsidian settings panel. You can use it to attri…

Language Access in Healthcare — Discourse Graph
Reason Commons | Reason Commons — Issue Trees & Logical Thinking Process

Issue-based information system
Logial Thinking Process (LTP) / Issue Tree App and Exploration - Issue Trees & Logical Thinking Process