Skip to content

Reading edition

AI and the Work of the Historian

Frédérick Madore

University of Kansas · 17 September 2026

11 slides

Contents

Slide 1

AI and Africa Symposium · University of Kansas · 17 September 2026

AI and the work
of the historian

Researching Islam and Muslims in West Africa.
Curating the sources through which we study them.

Slide 2

Abundance has a history

Collection items20,000+
Words in the textual corpus≈31 million
YouTube audiovisual minutes34,468
Items in my Zotero library38,142
islam.zmo.de/s/westafrica/page/homeOpen ↗

A familiar problem for historians: “scanning parties”, thousands of photographs, little time to read them.

Slide 3

Newly readable, still interpreted

Transcription and indexing in my workflow
Transcription
A readable text

Which spellings and uncertainties survive?

Indexing
A connected record

Do two names identify the same person?

Cataloguing
A findable collection

Which names and places get recorded?

Historical source criticism

A wrong transcription still reads well. Keep each transformation traceable to the document.

Slide 4

Reading printed Ewé

A 1976 page of the Togolese newspaper Togo Presse, printed in the Ewé language with full diacritics

Togo Presse, 31 July 1976.

Extracted text · Ewé
MIAFE ŊUTIFAFAFIA EYADEMA KPE TA KPLE MƆSLEMTƆWO FE ƉEKAWƆWƆ DƆDZIKPƆHA LA

Mia nɔvi Mɔslem hamea ngɔnɔlawo se nya xɔasiwo tso Togo yeyea fofo nu

«Woayra amesiwo léa avu la, elabena woayɔwo be Mawuviwo»

Enye Togo yeyea fofo avafiawodzifia Gnassingbe Eyadema fe didi vevi be amesiame nanɔ dzidzɔ kple ŋutifafa me lle yefe Denyigba la katã dzi, Dzre, fuéle kple mamãwo manɔ amewo kple habɔbɔwo domo o. Eyaŋuti dukplɔla Eyadema anukwaretɔ la lɔna ɖɔɖɔɖowo wɔwɔ edziedzi le dukɔmeviwo dome ɖo.

Ete ŋu dze edzi be miafe tatɔ nutefewɔla la do go kple mia nɔvi Mɔslem Hame fe amegãwo nyitsɔ le RPT fea me hena wodome nyawo sese,

Tototɔ kple dzre ɖo Mɔslem Hamea fe dɔdzikpɔha la me etefe didi. Ale mamã kple fuléle ɖo wo dome.

Le wofe anyinɔnɔa kple numeɖeɖeawo me na To o yeyea fofo vɔ megbe la, miafe ŋutifafa anukwaretɔ Eyadema ɖo asi Hamea fe dɔdzikpɔha la dzi elabenà ŋutif fa kple lɔlɔ̃ mele wo dome o

Eɖe nu me na Xɔsetɔawo be ɖekawɔwɔ kple ŋutifafa dim yele le yefe anyigba la dzi..,

Mlɔeba la dukplɔla la ɖo dɔléɖeasihaa ɖe, si me ame 17 le la na mia nɔviawo bena woadzra Mɔslemtɔwo fe takpekpe gã. si wɔ ge woala la le Lome le Dasiãmime 4 lia dzi la fe dɔwɔwɔwo ɖo,

Avafiawo Menveyinoyu Dzafalo, dũdɔnunɔla Lãmesẽ kple Hadomegbɛnɔnya-wogbɔkpɔla kple Ayaovi Asila, Togo tuakɔwo fe tatɔ kpeɖeŋutɔ hekpe ɖe dukplɔla fe dɔwɔfe dzikpɔla afɛtɔ Kpotivi Têvi Dzidzagbe Lacle ŋu woenɔ tatɔ Eyadema ŋu le Mɔslem Hamea fe nyawodɔdrɔ̃ me. Eye afɛtɔ Mama Fuseni kple Kasim Mensa, siwo nye Hamea fe bubu 'mewo la hã nɔ Takpekpea me nyitsɔ ma,

Slide 5

Building tools for the collection

AI-assisted coding

Generating and revising code through conversation.

Research decisions

Defining the task and checking what the tool counts, links and excludes.

The interface needs to be checked against the underlying records.

Slide 6

Where do the sources direct our attention?

IWAC · Places · All entities · Place bubblesOpen full screen

Explore the places most frequently mentioned in the IWAC—and the documents that mention them.

IWAC · 11 Sept 2026

Slide 7

What does a connection mean?

IWAC · Entity network · All types · All linksOpen full screen

A co-mention is a starting point for investigating a relationship.

IWAC · 11 Sept 2026

Slide 8

What should I read next?

IWAC · Sentiment analysis · Polarity · Centrality · SubjectivityOpen full screen

AI-assisted sentiment analysis · 12,349 newspaper articles

iwac.frederickmadore.com

Slide 9

Affordable access,
unequal control

Commercial servicesGemini · ChatGPT · Claude

Low entry costs, little local hardware.
Dependence on external providers.

Open-weight models

Increasingly capable alternatives.
Greater control when run locally.

Small models can run on personal computers; larger ones need substantial infrastructure.

Open weights do not mean equal access to computing resources.

Slide 10

Whose sources become usable?

  1. DigitisationFaster processing still depends on preservation and scanning.
  2. LanguageFrench-language gains are only a starting point.
  3. ExpertiseThe people who know the sources remain essential.

Slide 11

Expanding what
historians can do

More accessible sources. New tools.
New starting points for reading.

Historical judgement throughout.

The goal isn’t simply to process more sources,
but to help more people work with them.

Islam West Africa Collection