Research

New things


Profile Picture

What I do

I work on language and culture dynamics, using large corpora, machine learning & AI, and cognitive experiments. Recently I have been also collaborating on edtech, art history and creative industries projects, and advising cross-sector initiatives between academia and the public and private sectors. I am affiliated with Tallinn University as a lecturer in digital humanities and artificial intelligence (and a member of the CUDAN Cultural Data Analytics lab), with Estonian Business School as senior researcher, and the University of Tartu as an associate professor of computational social science, on the ERC funded RiDe project at the Deep Transitions lab. I did my PhD at the Centre for Language Evolution of the University of Edinburgh, on lexical dynamics and communicative need in language.
I also do consulting and workshops on R, stats & data visualization, and generative AI (see more here). I was recently granted the title of “Nationally Recognized Science Communicator” (riiklikult tunnustatud teaduse populariseerija) by the Estonian Science Foundation.


Research

Publications (including in-review preprints)

2026

  • Andres Karjus, Kais Allkivi, Silvia Maine, Katarin Leppik, Krister Kruusmaa, Merilin Aruvee. 2026. “Machine-Assisted Grading of Nationwide School-Leaving Essay Exams with LLMs and Statistical NLP” | preprint


2025 Machine-assisted quantitizing designs thumbnail

  • Thomas F. Eisenmann and Andres Karjus (joint first), Mar Canet Sola, Levin Brinkmann, Bramantyo Ibrahim Supriyatno, Iyad Rahwan. 2025. “Expertise elevates AI usage: experimental evidence comparing laypeople and professional artists” | preprint
  • Andres Karjus. 2025. “Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence”. Humanities and Social Sciences Communications 12 (1), 1-18 | open access
  • Andres Karjus. 2025. “Socioeconomic factors of national representation in the global film festival circuit: skewed toward the large and wealthy, but small countries can beat the odds”. Journal of Cultural Analytics | open access
  • Jonas M Nölle, Andres Karjus, Stefan Hartmann. 2025. “Evolutionary Linguistics” (upcoming chapter https://osf.io/download/rt5ha)
  • Tillmann Ohm, A Karjus, MV Tamm, M Schich. 2025. “fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings”. Scientific Data 12 (1), 254. | open access


2024 Divergence Paper Thumbnail

  • Andres Karjus and Christine Cuskley. 2024. Evolving Linguistic Divergence on Polarizing Social Media | Nature Humanities and Social Sciences Communications open access
  • Mark Mets, Andres Karjus, Indrek Ibrus, Maximilian Schich. 2023. Automated stance detection in complex topics and small languages: the challenging case of immigration in polarizing news media | PLOS One open access
  • Oiva, Mila, Ksenia Mukhina, Vejune Zemaityte, Tillmann Ohm, Mikhail Tamm, Andres Karjus, Mark Mets, Daniel Chávez Heras Mar Canet Solà, Helena Hanna Juht, Maximilian Schich. 2023. A Framework for the Analysis of Historical Newsreels | Nature Humanities and Social Sciences Communications open access
  • Yan Asadchy; Karjus, Andres; Mukhina, Ksenia; Schich, Maximilian. 2024. Perceived gendered self-representation on Tinder using machine learning | Nature Humanities and Social Sciences Communications open access
  • Tillmann Ohm, A Karjus, M Tamm, M Schich. 2024. fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings | preprint Cinando Paper Thumbnail
  • Andres Karjus, Vejune Zemaityte. 2024. Socioeconomic factors of national representation in the global film festival circuit: skewed toward the large and wealthy, but small countries can beat the odds | preprint
  • Vejune Zemaityte and Andres Karjus (co-first), Ulrike Rohn, Maximilian Schich, Indrek Ibrus. 2024. Quantifying the global film festival circuit: Networks, diversity, and public value creation | PLOS One open access | code, data & interactive dashboard


2023

  • Indrek Ibrus, Andres Karjus, Vejune Zemaityte, Ulrike Rohn, Maximilian Schich. 2023. Quantifying public value creation by public service media using big programming data. International Journal Of Communication, 17, 24. | open access
  • Juan Guerrero Montero, Andres Karjus, Kenny Smith, Richard A. Blythe. 2023. Reliable identification of selection mechanisms in language change. Corpus Linguistics and Linguistic Theory | Open access
  • Tillmann Ohm, Mar Canet Solà, Andres Karjus, Maximilian Schich. 2023. Collection Space Navigator: An Interactive Visualization Interface for Multidimensional Datasets. VINCI 2023: Proceedings of the 16th International Symposium on Visual Information Communication and Interaction. | open access | extended preprint | interactive demo | code Compression Paper Thumbnail
  • Andres Karjus, Mar Canet Solà, Tillmann Ohm, Sebastian Ahnert, Maximilian Schich. 2023. Compression ensembles quantify aesthetic complexity and the evolution of visual art. EPJ Data Science. 12, 21. | open access | code
  • Mehmet Burak Yilmaz, Elen Lotman, Andres Karjus, Pia Tikka. 2023. An embodiment of the cinematographer: emotional and perceptual responses to different camera movement techniques. Frontiers Neuroscience | open access | data


2022

  • Andres Karjus, Christine Cuskley. 2022. Evolving linguistic divergence in socio-political polarities. Proceedings of the Joint Conference on Language Evolution (JCoLE). | proceedings pdf


2021 Colexification Paper Thumbnail

  • Andres Karjus, Richard A. Blythe, Simon Kirby, Tianyu Wang, Kenny Smith. 2021. Conceptual similarity and communicative need shape colexification. Cognitive Science (open access) | bib | code and data


2020

  • Andres Karjus, 2020. Competition, selection and communicative need in language change. PhD thesis, University of Edinburgh | pdf | 1-page non-technical summary | eestikeelne lühikokkuvõte
  • Andres Karjus, Richard A. Blythe, Simon Kirby, Kenny Smith 2020. Communicative need modulates competition in language change | preprint
  • Andres Karjus, Richard A. Blythe, Simon Kirby, Kenny Smith 2020. Challenges in detecting evolutionary forces in language change using diachronic corpora. Glossa: a journal of general linguistics, 5(1), p.45. | open access | code
  • Andres Karjus, Richard A. Blythe, Simon Kirby, Kenny Smith, 2020. Quantifying the dynamics of topical fluctuations in language. Language Dynamics and Change 10(1), 86-125 | open access | code


2018

  • Andres Karjus, Martin Ehala, 2018. Testing an agent based model of language choice on sociolinguistic survey data. Language Dynamics and Change, 8, pp. 219-252 | journal link | open postprint | bib | sociolinguistic dataset: 1000 respondents, 200 questions
  • Andres Karjus, Richard A. Blythe, Simon Kirby, Kenny Smith, 2018. Topical advection as a baseline model for diachronic lexical dynamics. Proceedings of The Society for Computation in Linguistics. Volume 1. [extended abstract, full paper above] | open access | bib

2017

  • Martin Haspelmath, Andres Karjus, 2017. Explaining asymmetries in number marking: Singulatives, pluratives and usage frequency. Linguistics, volume 55, issue 6. | journal link | preprint | bib
         Show older…
  • Andres Karjus, 2015. Through the Spyglass of Synchrony: Grammaticalization of the Exterior Space in the Eastern Circum-Baltic. In: Hilpert, Martin, Östman, Jan-Ola, Mertzlufft, Christine, Rießler, Michael, Duke, Janet (eds.), Advances in Nordic Linguistics. De Gruyter Mouton. | google books
  • Andres Karjus (editor), 2013. Areal linguistics, Grammar and Contacts. Special issue of the Journal of Estonian and Finno-Ugric Linguistics, 4-2. Tartu: University of Tartu Press. | open access
  • Petar Kehayov, Eva Saar, Miina Norvik, Andres Karjus, 2013. Hääbuva kesklüüdi murde jälgedel suvel 2012 [On the footsteps of vanishing Central Lude in the summer of 2012]. Yearbook of the Estonian Mother Tongue Society, Vol. 58. | open access
  • Andres Karjus, 2012. Outdoors on the Shores of the Baltic: Gradience in the Grammaticalization of the Exterior-Region. Journal of Estonian and Finno-Ugric Linguistics 3-1, pp. 209-226.


Conferences & seminars (probably not complete list)

  • Talks on measuring the evolution of ideas around industrial modernity at DHNB2026 and Evolang2026
  • Talk at the CHR2026 in Luxembourg on rapid cultural analytics using LLMs and cross-sector collaboration
  • Invited talk at Grammar and Corpora 2025 on LLM-assisted corpus research
  • Coauthored talk on AI and art at the IC2S2 2025 in Sweden
  • Posters at DHNB 2025 in Tartu on media analytics using LLMs and AI-powered automated essay grading
  • Presentation and workshop at the Meertens Institute on AI in humanities
  • Poster at DHNB2024 in Iceland
  • Talk at the AI workshop we organized at Evolang (May 2024)
  • Talk on AI & humanities research at the 67. Kreutzwald Day conference in Tartu
  • Talk at the Cultural Data Analytics Conference 2023 14.12.2023 in Tallinn on using LLMs in a systematic mixed methods framework for large scale humanities & social science research | slides
  • Poster on AI & humanities research at the Computational Humanities Research conference CHR 2023 in Paris
         Show older…
  • Talk at the Tekstipäev (Day of the Text) in Tartu on AI & humanities research (30.11.2023)
  • Talk at the Tallinn University School of Humanities seminar on AI & humanities research
  • Seminar talk at the Change is Key project at the University of Gothenburg.
  • Talk on LLMs for studying texts and change at “Assessing and measuring systems change” workshop | slides
  • Poster on film festival research at Netsci 2023, Vienna
  • Presentation at the Bibliotheca Herziana workshop on computational approaches to art
  • Talk “Programming, data visualization & AI for academic audiences across institutions and disciplines: lessons learned”, at the Cross-university collaboration in Digital Humanities & Social Science (DHSS) and Digital Humanities & Cultural Heritage (DHCH) Education workshop of the DHNB2023 conference | slides
  • Talk “Exploring Estonian Public Television Production 2004-2020 Using Big Programming Data” at the 8th Estonian Digital Humanities Conference (05.10.2022)
  • Poster “Evolving Linguistic Divergence in Socio-Political Polarities”, at the JCoLe Joint Conference on Language Evolution in Kanazawa, Japan (August 2022)
  • Poster “Linguistic divergence in American English along socio-political polarities”, the IC2S2 Computational Social Science Conference (20.07.2022) | pdf
  • Seminar talk at the Poncelet laboratory in Moscow (November 2021)
  • Conference on Complex Systems 2021 (October 2021) | slides
  • Protolang 7 (September 2021) | slides
  • Culture Conference 2021 | Poster on aesthetic complexity
  • TÜling (April 2021)
  • Colloquium for Computational Linguistics and Linguistics in Stuttgart | Slides | Recording
  • RUSE 2019. Slides here.
  • CL2019. Slides here.
  • Culture Conference 2019, Poster here.
  • Inaugural ISLE workshop | Modelling lexical interactions in diachronic corpora | poster
  • University of Edinburgh Centre for Language Evolution seminar series | Challenges in detecting evolutionary forces in language change using diachronic corpora | slides | code
  • Corpus Linguistics in Scotland Network Meeting, Topical Fluctuations and Lexical Interactions in Diachronic Corpora
  • New directions in language evolution research workshop, at the SLE 2018 | Two problems and solutions in evolutionary corpus-based language dynamics research | slides with interactive plots | code
  • Applications in Cultural Evolution: Arts, Languages, Technologies | Selection above the baseline: quantifying the advection effect in four domains of cumulative culture | slides with interactive data&plots | code
  • Evolang 2018 | slides | open-access proceedings
  • Edinburgh Language Lunch
  • The inaugural meeting of the Society for Computation in Linguistics, part of LSA 2018 | download poster


Teaching


Private sector

I also teach workshops as an instructor and provide consulting in the private sector. These have taken the form of invited workshop and seminars, standalone events, or components of conferences, summer schools or academic retreats. Feel free to get in touch if you are interested in talking about organizing a workshop on anything related to data science and statistics, digital skills, artificial intelligence, AI assistants like Codex, data visualization, R, corpus linguistics, digital humanities, etc.
For more details, pricing and contact, head over to datafigure.eu

Academic teaching

My position now includes some teaching activities on digital skills and AI at Tallinn University, and I do occasional guest lectures; recently for the Data Science and Digital Humanities programme at the University of Tartu and for the Cultural Data Analytics I and II courses at Tallinn University.

Past teaching

  • I was engaged in teaching stats and R to Edinburgh Uni psychology masters students 2017-2019.
  • And worked for the Edinburgh University School of Psychology, Philosophy and Language Sciences Writing Centre 2017-2020 as awritten communication consultant, specializing in writing about and presenting data and data analysis results.
  • Developed and co-taught a course on data analysis for digital humanities at the University of Tartu in the spring of 2016.
  • Lectured on corpus linguistics and R for the Academia Salensis summer school of 2015.
  • Worked as a teaching assistant for courses on language technology and artificial intelligence, Department of Computer Science, University of Tartu, 2014-2016.

Academic advisory

I also serve on a number of academic advisory board type things:

  • AI Advisory Board (Tehisintellekti nõukoda) of Tallinn University, and Research board of the Humanities department
  • R&D board and senate of EBS
  • Program committee of the EKKD funding scheme of the Estonian Science Foundation
  • Digital Heritage Board of the Ministry of Culture
  • Editorial board of the Computational Humanities Research journal
  • In the past I’ve served as student rep on institutional boards of the University of Tartu and KU Leuven, and the board of the Digital Humanities in the Nordics and Baltics organization.


Popsci & misc


Various essays, media appearances and interviews in Estonian media:

  • Appeared in the “Õhtu!” (Evening!) talk show of the Estonian Kanal2 TV channel to talk about AI risks (December 2025)
  • Story in the Estonian ERR on AI-powered analytics
  • Was awarded the “Nationally Recognized Science Communicator” (riiklikult tunnustatud teaduse populariseerija) title at the annual Science Popularization prize 2024 of the Estonian Science Foundation | press
  • Wrote an essay on AI and humanities for Sirp
  • Appeared in Kultuuristuudio on ETV2 TV channel
  • Appeared in Raadio2 “Päev” radio segment on training AI
  • “1 minute science” video segment in Novaator on using AI and ML in humanities
  • An essay with colleagues in Sirp on humanities and AI
  • A piece on AI and education, with colleagues in the Estonian culture journal Sirp
  • Wrote an opinion piece in ERR Novaator on how generative AI will affect education in the near future (16.06.2023)
  • Gave a number of interviews on artificial intelligence and education topics in 2023 (in Estonian): Kanal2 Õhtu, Äripäev radio, TÜHI Eeter podcast, PostimeesTV, BFM Luna TV, Postimees
  • News piece in Pealinn on Tallinn city enterpreneurship prizes 2022, including me & colleagues for our media monitoring AI prototype in collaboration with AS Ekspress Grupp.
  • Hosted students at the CUDAN lab via the job shadowing (töövari) programme of the Estonian Tagasi Kooli programme (online April 2021, live in November 2020).
  • I helped my supervisor Prof. Kenny Smith carry out a number of linguistics workshops in primary schools around Edinburgh and Lothian, in school years 2018/2019 and 2019/2020.
  • Entered a video to Science Magazine’s 11th Dance Your Ph.D contest. The idea is to explain your research topic to the general public though interpretive dance. We didn’t win but it was a fun one to do!
  • Co-organized the bimonthly Edinburgh Language Lunch during 2016-2018.
  • Co-organized the Linguistics and English Language Postgraduate Conference of 2017 in Edinburgh, the Why Linguistics Conference (2015) and the Graduate Conference on Areal Linguistics, Grammar and Contacts (2012) in Tartu, Estonia.


Distant past

In the more distant past before the PhD in Edinburgh, I worked as a teaching assistant in informatics at the University of Tartu (2015-2016), before that studied artificial intelligence and natural language processing at KU Leuven (MSc) and linguistics at the University of Tartu (BA, MA). I was also affiliated 2016-2019 as a (part-time) junior researcher with the University of Tartu EKKAM sociolinguistics group, doing data analysis and agent-based models. During my pre-PhD studies I also went on exchanges to the University of Iceland and the University Vienna, attended a dozen-odd academic summer schools, taught Icelandic to art students and Estonian to Norwegian teachers, worked as an assistant at the Estonian Wordnet project, and did internships at CrossLang NV in Belgium and at (the old) Linguistics Departent of the Max Planck Institute for Evolutionary Anthropology in Leipzig. In earlier years, I worked various studenty sort of jobs to support my studies (for a seller of swords, for a seller of cars, for a minder of horses and tourists).


Contact




Andres Karjus

PhD, MA (linguistics), MSc (artificial intelligence)

Lecturer in digital humanities and AI at Tallinn University
Senior research fellow at Estonian Business School
Associate professor of computational social science at the University of Tartu
Instructor at Datafigure OÜ

Academic email: andres.karjus –at– tlu.ee
Business and workshop inquiries: kindly email via the Datafigure contacts


LinkedIn: www.linkedin.com/in/andreskarjus/
Bluesky: bsky.app/profile/andreskarjus.bsky.social
Google Scholar profile
Twitter/X twitter.com/AndresKarjus
Mastodon: mastodon.social/@AndresKarjus