We're officially launching the new PSL CultureLab in 10 days ! If you're interested in the research of a collective bridging Computational Humanities, Social Sciences and Cultural Evolution, you can check our programme (and come to our event, if you're in Paris 22 September): psl.eu/agenda/collo...

✍️ Our paper is finally out! All poetic forms come from somewhere, but figuring out their relationships is hard. We use sequence alignment on scansion (010.10) to measure metrical similarity between poems. This allows us to detect related forms across languages and times 1/ tinyurl.com/metronome25

New this morning, a Comment I contributed to Nature Computational Science on the interaction between large language models and the humanities. 🧪 🤖 #MLSky rdcu.be/etk07 The link above will be open-access for a month — plus, I'll reply to this post with a link to a permanently open preprint. +

I had fun presenting some of my PhD obsessions about the french detective novel in Würzburg. Thank you @fotisjannidis.bsky.social for the invitation ! The whole team is impressive, brand new building and talented people, the future of DH is actually here 🤩

"Tell, Don't Show" was accepted to #ACL2025 Findings! 

 Our conceptually intuitive, lightweight approach for literary topic modeling combines the new (language models) with the old (classic LDA) to yield better topics. ✨📚 arxiv.org/abs/2505.23166

New little paper “The times are a-changin’: présent vs passé simple in French novels (1811–2024)”👉 hal.science/hal-04984105 With Simon Gabay and @floriancafiero.bsky.social #dhbenelux2025 In french fiction, use of past tenses (especially the passé simple) collapsed over the last 150 years.. so why?

🚨New pre-print 🚨 News articles often convey different things in text vs. image. Recent work in computational framing analysis has analysed the article text but the corresponding images in those articles have been overlooked. We propose multi-modal framing analysis of news: arxiv.org/abs/2503.20960

🚨 Our Call for Papers is out! 🚨 We continue our tradition of providing a dedicated platform for presenting computational work that bridges formal methods and traditional inquiry in the arts and humanities. Check out the website for all details: 2025.computational-humanities-research.org/cfp/

Le Monde reporting that a French scientist traveling to Houston to attend a conference was denied entry to US after a search of his phone & computer revealed messages critical of Trump's science cuts, "which [says CPB] conveyed hatred of Trump & could be qualified as terrorism". Computer confiscated

Excited to share our preprint "Provocations from the Humanities for Generative AI Research” We're open to feedback—read & share thoughts! @laurenfklein.bsky.social @mmvty.bsky.social @docdre.distributedblackness.net @mariaa.bsky.social @jmjafrx.bsky.social @nolauren.bsky.social @dmimno.bsky.social

New cultural evolution modelling paper with @bdecourson.bsky.social on @pnas.org! "Weak individual preferences stabilize culture" A quick 🧵 www.pnas.org/doi/10.1073/...

Change over time is often depicted as a trendline. But what does shape a trendline? Which forces? Our new paper presents a method allowing to “decompose” trendlines into constituent forces. Also, we tackle an old puzzle: Does culture change “one funeral at a time”? 🧵(1/8) doi.org/10.1098/rspb...

[clearing throat]

My video on spaCy layout is now out! This is probably my favorite update from @explosion-ai.bsky.social (and that's saying something!) This package makes it simple to do region detection, table detection, and OCR with just 1 line of Python. Video: youtu.be/quJtzVxoMtE #MachineLearning

I'll get straight to the point. We trained 2 new models. Like BERT, but modern. ModernBERT. Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff. It's much faster, more accurate, longer context, and more useful. 🧵

“They said it could not be done”. We’re releasing Pleias 1.0, the first suite of models trained on open data (either permissibly licensed or uncopyrighted): Pleias-3b, Pleias-1b and Pleias-350m, all based on the two trillion tokens set from Common Corpus.

Thank you #chr2024 ! What a week 🤩 - problem now is that I have 15 new article ideas, and I might write 4 new PhD proposals 😭

What a session 😍! thank you @mariaa.bsky.social for the thread !

Now @jbarre.bsky.social speaking about "Latent Structures of Intertextuality in French Fiction." This paper explores genre classification and text similarity over time. One clear finding: canonical novels are more similar to what comes after them, compared to non-canonical novels. #chr2024

The #CHR2024 workshops were once again a success! I particularly liked when @Yuri Bizzoni casually said: "Let's calculate GPT2 perplexity on canonical texts and see what happens"

I made a starter pack for grad students in DH, to build visibility for a rising group of scholars. If you want to be added (or know someone who should be), just comment! go.bsky.app/8Bju8SY

There are many ways to identify texts that seem ahead of their time. Our CHR 2024 paper asks which measures of textual precocity align best with social evidence about influence and change.

🚀📢 BookNLP-fr is here! A major step for french computational literary studies by the Lattice Lab team—Frédérique, Olga, Martial, Clément, @tpoibeau.bsky.social and I! 🌍 The French expansion of @dbamman.bsky.social’s BookNLP project 📖 doi.org/10.48694/jcl... #ComputationalHumanities #NLP

Our proceedings are out! 🚨 They include no less than 78 papers that reflect the diverse and innovative research happening within the Computational Humanities. Take a dive here: ceur-ws.org/Vol-3834/

Releasing two trillion tokens in the open. huggingface.co/blog/Pclangl...

can anyone make a stop worrying starter pack

🔍 The full program for #CHR2024 is now available! Join us for cutting-edge computational humanities research and discussions. See the complete schedule at: 2024.computational-humanities-research.org/programme/

Didn't find one, so made a computational literary studies starter pack, with notable bunch of european folks and early career scholars. My circle here is small, so please reply/dm to be added or removed and suggest people from your networks! go.bsky.app/4et1nxZ

Big new paper out today! In which we use the 2021 DMCA exemption for text and data mining to build a new large collection of film and measure representation for gender and race/ethnicity within it. (w/ @ucbscholcomm.bsky.social @richardjeanso.bsky.social @naitian.org) www.pnas.org/doi/10.1073/...

Finally my book has a cover! Digital Social Reading: Sharing Fiction in the 21st Century. Out 21 January 2025 in open access. mitpress.mit.edu/978026255091... #culturalanalytics @unigroningen.bsky.social

Happy to announce that Pleias is joining The AI Alliance to Co-lead the Open Trusted Data Initiative. We will release on November 11th the largest multilingual fully open dataset for LLM training with 2 trillion tokens on HuggingFace and The Alliance OTDI.

With Catherine Arnett, Elliot Jones and Ivan Yamshchikov we are releasing a missing block to pretrain language models on cultural heritage: Detoxifying the Commons. arxiv.org/pdf/2410.22587

How has textuality been shaped over time? In this new article, we propose a very distant reading /quantitative analysis showing that both Canon and Genres have an impact on textuality. arxiv.org/abs/2410.17759

And the publication series continues: Today we announce the sixth article from JCLS 3 (1): Feldkamp et al. "Measuring Literary Quality. Proxies and Perspectives" (10.48694/jcls.3908). Check it out at: jcls.io/issue/109/in... #ComputationalLiteraryStudies #CLS #JCLS #DigitalHumanities #CCLS24

Curious about the Journal of Compuational Literary Studies? We just published our most recent Call for Papers for next year's conference track. Check it out at: jcls.io/site/cfp/ #CfP #CCLS25 #JCLS #journal #OpenAccess #DigitalHumanities #ComputationalLiteraryStudies #Krakow

Our paper was accepted at EMNLP Findings! V excited for this work to be published. Stay tuned for the final version ✨ Such a fun collab w/ @mariaa.bsky.social and Anna Preus

Our new paper is out that describes PoeTree ✒️🌳 dataset: a large collection of European poetry in 10 languages. All data are open; API, R & Python libraries, or query the whole thing on our website 📝 Paper: tinyurl.com/jdhss 🌍 Web browser: tinyurl.com/poetreeweb 💽 Full data: tinyurl.com/ptzenodo

better late than never 😋

How is agency distributed between characters in fiction writing? In a new PNAS paper, I present a large-scale analysis of the interaction networks of 87,531 fiction works written between 1850 and 2010. What I found is an “agency gap”… Here's a rundown of my findings: 1/ www.pnas.org/doi/epdf/10....

📢 #CHR2024 Deadline Alert! 📅 July 8 is just around the corner for paper submissions to the Computational Humanities Research conference in Aarhus. 🏃‍♀️💨 Polish those drafts or sprint to the finish line! More details at: 2024.computational-humanities-research.org/cfp/ #ComputationalHumanities

💥 NEW preprint from me and the computational poetics gang: the writeup of my wacky 'what if poetic meters were like DNA?' idea. We use the 'metronome' to find systemic metrical oddities, group related forms across languages, and do some Renaissance phylogeny.

New blog post ! "LLMs in Quest for Adventure" 👉 huggingface.co/blog/crazyje... 👈 First experiments with LLMs, trying to evaluate how they can be useful for computational literary studies. Here we focus on the detection of stereotypical scenes in adventure novel.

"Disentangling Semantic and Prosodic Features of English Poetry," authored by @tedunderwood.me and me, is available as an open-access publication in Digital Scholarship in the Humanities: doi.org/10.1093/llc/.... We classified 30k+ English poems to study the distinction between genre and form. (1/6)

We are very happy to publicly release the CATMuS Medieval dataset on @huggingface.bsky.social : huggingface.co/datasets/CAT... This dataset is unique in the space of HTR, as it includes more 160 000 lines of ground truth in 10 languages over 9 centuries (8-16 CE) in Latin scripts over 208 docs.

What is the unemployment rate in... drama? Corpus of Alsatian drama allows to look at how characters are socially coded. Interestingly, trends for female and male characters diverge: the more "space" a male character takes, the more likely they'll have a job; the opposite happens for women.

Cool look at novelty in French literature over time from Jean Barré @jbarre at #CHR2023

Then @jbarre.bsky.social , Olga Semnick, Frédérique Mélanie, and @tpoibeau.bsky.social led us through a series of questions about gender and adventure in French fiction, using a range of different NLP methods.

Fascinating presentation by @tedunderwood.me this afternoon: LLMs as a creative way to operationalize plot predictability, an Achilles heel in computational literary studies until now

Is it possible to identify key authors and novels that have had an impact on literary change? Are those names present in our contemporary literary canon? New article out w @tpoibeau.bsky.social: "Beyond Canonicity. Modeling Canon/Archive Literary Change in French Fiction" ceur-ws.org/Vol-3558/pap...