AKAndres Karjus

Andres Karjus

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andres Karjus has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    Expertise Elevates AI Usage: Experimental Evidence Comparing Laypeople and Professional Artists

    by Thomas F. Eisenmann, Andres Karjus, Mar Canet Sola, Levin Brinkmann, Bramantyo Ibrahim Supriyatno, Iyad Rahwan

    1. Generative machine learning models’ increasing prevalence and capacities are transforming creative processes. Large language model-driven text generators and chatbots like ChatGPT or Copilot ena...


  • Open Access

    Socioeconomic factors of national representation in the global film festival circuit: skewed toward the large and wealthy, but small countries can beat the odds

    by Andres Karjus, Vejune Zemaityte

    This study analyzes how economic, demographic, and geographic factors predict the representation of different countries in the global film festival circuit. It relies on the combination of several open-access databases, including festival programming information from the Cinando platform of the Cannes Film Market. The dataset consists of over 20,000 unique films from almost 600 festivals across the world over a decade, a total of more than 30,000 film festival entries. It is shown that while films from large affluent countries indeed dominate the festival screen, the bias is nevertheless not fully proportional to the large demographic and economic worldwide disparities and that several smaller countries perform better than expected. Further computational simulations demonstrate how much including films from smaller countries contributes to cultural diversity, and how countries vary in cultural “trade balance” dynamics, revealing differences between net exporters and importers of festival films. This research underscores the importance of representation in film festivals and the public value of increasing cultural diversity. The data-driven insights and quantitative approaches to festival programming and cultural event analytics should be useful for both the academic community as well as film festival organizers and policymakers aiming to foster more inclusive and diverse cultural landscapes.

  • Open Access

    Evolutionary Linguistics

    by Jonas Nölle, Andres Karjus, Stefan Hartmann

    Evolutionary linguistics studies the origins and evolution of human language using a broad variety of approaches and methods from multiple different disciplines. This chapter reviews current approaches to the origins and evolution of language, and gives an overview of methods that have been developed to investigate how language has evolved from non-human communication systems, and how it has developed over time. In particular, we take into account comparative studies with animal communication systems, anthropological and paleontological evidence, as well as experimental, corpus-based, and computational modeling approaches.(This is an extended preprint of our contribution to the Encyclopedia of Language and Linguistics, 3rd edition.)

  • Top Cited Papers
    Open Access

    Machine-assisted quantitizing designs: augmenting humanities and social sciences with artificial intelligence

    by Andres Karjus

    The increasing capacities of large language models (LLMs) have been shown to present an unprecedented opportunity to scale up data analytics in the humanities and social sciences, by automating complex qualitative tasks otherwise typically carried out by human researchers. While numerous benchmarking studies have assessed the analytic prowess of LLMs, there is less focus on operationalizing this capacity for inference and hypothesis testing. Addressing this challenge, a systematic framework is argued for here, building on mixed methods quantitizing and converting design principles, and feature analysis from linguistics, to transparently integrate human expertise and machine scalability. Replicability and statistical robustness are discussed, including how to incorporate machine annotator error rates in subsequent inference. The approach is discussed and demonstrated in over a dozen LLM-assisted case studies, covering nine diverse languages, multiple disciplines and tasks, including analysis of themes, stances, ideas, and genre compositions; linguistic and semantic annotation, interviews, text mining and event cause inference in noisy historical data, literary social network construction, metadata imputation, and multimodal visual cultural analytics. Using hypothesis-driven topic classification instead of “distant reading” is discussed. The replications among the experiments also illustrate how tasks previously requiring protracted team effort or complex computational pipelines can now be accomplished by an LLM-assisted scholar in a fraction of the time. Importantly, the approach is not intended to replace, but to augment and scale researcher expertise and analytic practices. With these opportunities in sight, qualitative skills and the ability to pose insightful questions have arguably never been more critical.


  • Open Access

    Perceived gendered self-representation on Tinder using machine learning

    by Yan Asadchy, Andres Karjus, Ksenia Mukhina, Maximilian Schich


  • Top Cited Papers
    Open Access

    Automated stance detection in complex topics and small languages: The challenging case of immigration in polarizing news media

    by Mark Mets, Andres Karjus, Indrek Ibrus, Maximilian Schich

    Automated stance detection and related machine learning methods can provide useful insights for media monitoring and academic research. Many of these approaches require annotated training datasets, which limits their applicability for languages where these may not be readily available. This paper explores the applicability of large language models for automated stance detection in a challenging scenario, involving a morphologically complex, lower-resource language, and a socio-culturally complex topic, immigration. If the approach works in this case, it can be expected to perform as well or better in less demanding scenarios. We annotate a large set of pro- and anti-immigration examples to train and compare the performance of multiple language models. We also probe the usability of GPT-3.5 (that powers ChatGPT) as an instructable zero-shot classifier for the same task. The supervised models achieve acceptable performance, but GPT-3.5 yields similar accuracy. As the latter does not require tuning with annotated data, it constitutes a potentially simpler and cheaper alternative for text classification tasks, including in lower-resource languages. We further use the best-performing supervised model to investigate diachronic trends over seven years in two corpora of Estonian mainstream and right-wing populist news sources, demonstrating the applicability of automated stance detection for news analytics and media monitoring settings even in lower-resource scenarios, and discuss correspondences between stance changes and real-world events.


  • Top Cited Papers
    Open Access

    A framework for the analysis of historical newsreels

    by Mila Oiva, Ksenia Mukhina, Vejune Zemaityte, Andres Karjus, Mikhail Tamm, Tillmann Ohm, Mark Mets, Daniel Chávez Heras, Mar Canet Sola, Helena Hanna Juht, et al.

    Audiovisual news is a critical cultural phenomenon that has been influencing audience worldviews for more than a hundred years. To understand historical trends in multimodal audiovisual news, we need to explore them longitudinally using large sets of data. Despite promising developments in film history, computational video analysis, and other relevant fields, current research streams have limitations related to the scope of data used, the systematism of analysis, and the modalities and elements to be studied in audiovisual material and its metadata. Simultaneously, each disciplinary approach contributes significant input to research reducing these limitations. We therefore advocate for combining the strengths of several disciplines. Here we propose a multidisciplinary framework for systematically studying large collections of historical audiovisual news to gain a coherent picture of their temporal dynamics, cultural diversity, and potential societal effects across several quantitative and qualitative dimensions of analysis. By using newsreels as an example of such complex historically formed data, we combine the context crucial to qualitative approaches with the systematicity and ability to cover large amounts of data from quantitative methods. The framework template for historical newsreels is exemplified by a case study of the “News of the Day” newsreel series produced in the Soviet Union during 1944–1992. The proposed framework enables a more nuanced analysis of longitudinal collections of audiovisual news, expanding our understanding of the dynamics of global knowledge cultures.


  • Open Access

    Evolving linguistic divergence on polarizing social media

    by Andres Karjus, Christine Cuskley

    Language change is influenced by many factors, but often starts from synchronic variation, where multiple linguistic patterns or forms coexist, or where different speech communities use language in increasingly different ways. Besides regional or economic reasons, communities may form and segregate based on political alignment. The latter, referred to as political polarization, is of growing societal concern across the world. Here we map and quantify linguistic divergence across the partisan left-right divide in the United States, using social media data. We develop a general methodology to delineate (social) media users by their political preference, based on which (potentially biased) news media accounts they do and do not follow on a given platform. Our data consists of 1.5M short posts by 10k users (about 20M words) from the social media platform Twitter (now “X”). Delineating this sample involved mining the platform for the lists of followers (n = 422M) of 72 large news media accounts. We quantify divergence in topics of conversation and word frequencies, messaging sentiment, and lexical semantics of words and emoji. We find signs of linguistic divergence across all these aspects, especially in topics and themes of conversation, in line with previous research. While US American English remains largely intelligible within its large speech community, our findings point at areas where miscommunication may eventually arise given ongoing polarization and therefore potential linguistic divergence. Our flexible methodology — combining data mining, lexicostatistics, machine learning, large language models and a systematic human annotation approach — is largely language and platform agnostic. In other words, while we focus here on US political divides and US English, the same approach is applicable to other countries, languages, and social media platforms.


  • Open Access

    Quantifying the global film festival circuit: Networks, diversity, and public value creation

    by Vejune Zemaityte, Andres Karjus, Ulrike Rohn, Maximilian Schich, Indrek Ibrus

    Film festivals are a key component in the global film industry in terms of trendsetting, publicity, trade, and collaboration. We present an unprecedented analysis of the international film festival circuit, which has so far remained relatively understudied quantitatively, partly due to the limited availability of suitable data sets. We use large-scale data from the Cinando platform of the Cannes Film Market, widely used by industry professionals. We explicitly model festival events as a global network connected by shared films and quantify festivals as aggregates of the metadata of their showcased films. Importantly, we argue against using simple count distributions for discrete labels such as language or production country, as such categories are typically not equidistant. Rather, we propose embedding them in continuous latent vector spaces. We demonstrate how these “festival embeddings” provide insight into changes in programmed content over time, predict festival connections, and can be used to measure diversity in film festival programming across various cultural, social, and geographical variables—which all constitute an aspect of public value creation by film festivals. Our results provide a novel mapping of the film festival circuit between 2009–2021 (616 festivals, 31,989 unique films), highlighting festival types that occupy specific niches, diverse series, and those that evolve over time. We also discuss how these quantitative findings fit into media studies and research on public value creation by cultural industries. With festivals occupying a central position in the film industry, investigations into the data they generate hold opportunities for researchers to better understand industry dynamics and cultural impact, and for organizers, policymakers, and industry actors to make more informed, data-driven decisions. We hope our proposed methodological approach to festival data paves way for more comprehensive film festival studies and large-scale quantitative cultural event analytics in general.


  • Open Access

    Perceived Gendered Self-Representation on Tinder Using Machine Learning

    by Yan Asadchy, Andres Karjus, Ksenia Mukhina, Maximilian Schich

    This paper explores the gendered differences between men and women as perceived through the images on the online dating platform Tinder. While research on personal images on Instagram, Tumblr, and Facebook has been studied en mass, large-scale studies of the landscape of visual representation on online dating platforms are rare. We apply a machine learning algorithm to 10680 profile images collected on Tinder in Estonia to study the perceived gendered differences in self-representation among men and women. Beyond identifying the dominant genres of profile pictures used by men and women, we build a comprehensive map of visual self-representation on the platform. We further expand our findings by analyzing the distribution of the image genres across the profile gallery and identifying the prevalent positions for each genre within the profiles. Lastly, we identify the variability of women's and men's images within each genre. Our approach provides a holistic overview of the culture of visual self-representation on the dating app Tinder and invites scholars to expand the research on gendered differences and stereotypes to include cross-platform and cross-cultural analysis.