iiinova — where your digital self keeps evolving

Thanks Katie! The method is very much based on MapReader so would love to talk more soon!

010

Thanks! That would be awesome! Have become very interested in 'kreupelhout' over the last weeks.

010

What (hopefully) makes this approach valuable is its potential to be applied to similar photograph collections worldwide. Many colonial powers created aerial archives across the Global South, and digital methods offer new ways to study environmental transformation at unprecedented scales.

020

The project essentially turns tools of territorial control into sources of historical understanding. These aerial surveys were designed to facilitate extraction and administration, but they also captured environmental realities the colonizers didn't necessarily intend to document.

100

But this isn't just about colonial power. Analyzing at scale also reveals persistence, adaptation, and resistance by indigenous communities—patterns that individual photographs might miss but become visible when you look at thousands of images systematically.

100

I'll develop an AI-powered method to analyze these photographs at scale—examining the sweeping transformation of the Indonesian environment through plantations, mines, roads, and other colonial infrastructure.

100

Thomas Smits @thomassmits.bsky.social · 10/12/2025

Pleased to share that I've been awarded an NWO XS grant for "Terraforming from Above: Digital Methods for Colonial Aerial Photography" Between 1920-1949, Dutch pilots systematically photographed Indonesia from above, creating an unprecedented aerial archive of the colonial landscape.

6145

If that's not enough to convince you, @nolauren.bsky.social/@taylor-arnold.bsky.social investigate pacing in 4,500 US sitcom episodes and Kaspar Beelen/Natasha Kitcher show us how we can link museum data with AI. edu.nl/mgdud edu.nl/349v9

051

Thomas Smits @thomassmits.bsky.social · 10/12/2025

In the same session, @lorenverreyen.bsky.social presents a dataset of 412 days of automatically transcribed podcasts. Hugely important work that allows us to study podcasts w. techniques from comp lit studies and takes the next step in the multimodal turn in computational humanities. edu.nl/7w4fg

151

Thomas Smits @thomassmits.bsky.social · 10/12/2025

Excited for session 2B this afternoon at #CHR2025! @melvinwevers.bsky.social presents our work (w. @folgertk.bsky.social) using Faith's Phylogenetic Diversity to quantify archival silence and bias. We're measuring the diversity of the Dutch National Archive's photographic collection. edu.nl/7cbef

1184

Reposted by Thomas Smits

Daniel van Strien @danielvanstrien.bsky.social · 21/11/2025

Building datasets to train smaller, task-focused models used to be incredibly time-consuming. Very excited to see SAM3 massively lower that barrier. Describe the class you want to detect and get annotated datasets automatically! Try it yourself: huggingface.co/datasets/uv-...!

Screenshot of a simple app showing bounding boxes for photographs detected in historic newspaper images.

$hf jobs uv run \ --flavor a100-large \ -s HF_TOKEN=HF_TOKEN \ https://huggingface.co/datasets/uv-scripts/sam3/raw/main/detect-objects.py \ -- davanstrien/newspapers-with-images-after-photography-big \ davanstrien/newspapers-photo-predictions \ --class-name "photograph" \ --confidence-threshold 0.4$

15712

Reposted by Thomas Smits

Computational Humanities Research @comphumresearch.bsky.social · 19/11/2025

📢 The #CHR2025 proceedings are out! 97 papers, ~1600 pages of computational humanities 🔥 Now published via the new Anthology of Computers and the Humanities, with DOIs for every paper. 🔗 anthology.ach.org/volumes/vol0... And don’t forget: registration closes tomorrow (20 Nov)!

anthology.ach.org

Edited by Taylor Arnold, Margherita Fantoli, and Ruben Ros

05641

Reposted by Thomas Smits

Daniel Wilson @danielwilson.bsky.social · 11/11/2025

!Stop Press! Article on bias in digitised newspaper collections: ’Whose News’, in the new journal of @comphumresearch.bsky.social by Kaspar Beelen, @jonhistorian61.bsky.social, @kmcdono.bsky.social and me. See blog for summary & 🧵 1/7 Article doi.org/10.1017/chr.... Blog is.gd/2IFc30 #dh #c19 🗃️

doi.org

Whose news? Critical methods for assessing bias in large historical datasets | Computational Humanities Research | Cambridge Core

Whose news? Critical methods for assessing bias in large historical datasets - Volume 1

12618

Reposted by Thomas Smits

James Baker @jwbaker.bsky.social · 23/09/2025

Look at our lovely autumn/winter @ihr.bsky.social Digital History seminar schedule, including talks from @bamcshane.bsky.social @jeroenputtevils.bsky.social @rubenros.bsky.social @thomassmits.bsky.social @melvinwevers.bsky.social and more! #dhist

02918

Reposted by Thomas Smits

Pete Orford @peteorford.bsky.social · 17/09/2025

Victorianists - a little bit of silly joy in all the gloom: take a moment today to vote for this gorgeous Lego set idea of the Great Exhibition so we can all get it for Christmas! beta.ideas.lego.com/product-idea...

Front view of the Crystal Palace exterior rendered in Lego complete with megalosaurus and horsedrawn omnibus

Interior view of Lego Crystal Palace showing various details of the exhibition

44417

Thomas Smits @thomassmits.bsky.social · 29/08/2025

A great critique! I do wish that historians would use their anger at this article to start to think more about corpus delimitation and methods. Critiquing this kind of work is easy if you don't feel the need to explicate your methods or data (obs. not applicable to you!)

140

Reposted by Thomas Smits

Katie McDonough @kmcdono.bsky.social · 16/07/2025

Excited to hear "Mapping Empire: A Distant Viewing Approach to News Maps in Victorian Illustrated Periodicals, 1842-1890" from Bethany Warner & @thomassmits.bsky.social next!

152

Thomas Smits @thomassmits.bsky.social · 26/06/2025

Can you see this list? archive.org/download/gra... I also downloaded the issue for you, please find it here: filesender.surf.nl?s=download&t...

filesender.surf.nl

SURFfilesender

Thomas Smits @thomassmits.bsky.social · 26/06/2025

Maybe I can take this oppurtunity to promote our open-access dataset of the Illustrated London News and multimodal search tool: bsky.app/profile/thom... Search the images of the ILN (1842-1889) with words or images. Easy install via Github but also happy to help with some image quests!

121

Thomas Smits @thomassmits.bsky.social · 26/06/2025

Hi Efram, I think this is not from the ILN but the Graphic. Using our multimodal AI ILN search tool (github.com/tpsmi/ilnmul...) I did find this image from the same trial in ILN (21-10-27)

000

Ik kan niet voor de huidige redactie spreken en ga nu weer stoppen want had me juist voorgenomen om geen (semi-)politieke discussies hier te voeren. Kijk uit naar je stuk!

Volgens mij zijn we het eens dat wetenschap om waarheid moet gaan maar verlangen dat iedereen met een links signatuur zich 'strategisch' niet uitspreekt over de politieke dimensie van de geschiedenis vind ik naïef (en principieel onjuist).

Wetenschap moet neutraal blijven maar van platforms als OdM, die altijd inherent politiek waren en daar nooit geheim van hebben gemaakt, neutraliteit eisen vind ik een naïef zwaktebod (zeker in huidige tijden).

100

Er bestaat niet zoiets als 'verder politiseren'. Als een partij een discussie politiek heeft gemaakt, kan je daar geen non politieke discussie meer over voeren: het speelbord is dan al ongelijk met andere regels voor de verschillende partijen.

200

Ik zou zeggen doe het vizier open: wetenschap moet gaan over waarheid maar platforms als OdM kunnen (en moeten misschien wel) een discussie die toch als zwaar gepolitiseerd is niet uit de weggaan. Je positie baseren op wat extreemrechts als verwijt kan inzitten werkt overduidelijk niet.

Ik vind het 'strategisch' onhandig argument al lang niet meer opgaan. Aan de ene kant zeg je, dat we ons strategisch niet moeten uitspreken maar aan de andere kant onderken je dat extreemrechts ook zonder enige basis de historische wetenschap als 'links' / 'woke' etc wegzet.

Vraag me af of - tegen de achtergrond van de opkomst van extreemrechts - dit de discussie is die je als historische gemeenschap wil voeren. Het staat je toch ook gewoon vrij om niks in te sturen (een andere pad te bewandelen)?