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

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.

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

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.

Dissecting landscape art history with information theory.

Painting has played a major role in human expression, evolving subject to a complex interplay of representational conventions, social interactions, and a process of historization. From individual qualitative work of art historians emerges a metanarrative that remains difficult to evaluate in its validity regarding emergent macroscopic and underlying microscopic dynamics. The full scope of granular data, the summary statistics, and consequently, also their bias simply lie beyond the cognitive limit of individual qualitative human scholarship. Yet, a more quantitative understanding is still lacking, driven by a lack of data and a persistent dominance of qualitative scholarship in art history. Here, we show that quantitative analyses of creative processes in landscape painting can shed light, provide a systematic verification, and allow for questioning the emerging metanarrative. Using a quasicanonical benchmark dataset of 14,912 landscape paintings, covering a period from the Western renaissance to contemporary art, we systematically analyze the evolution of compositional proportion via a simple yet coherent information-theoretic dissection method that captures iterations of the dominant horizontal and vertical partition directions. Tracing frequency distributions of seemingly preferred compositions across several conceptual dimensions, we find that dominant dissection ratios can serve as a meaningful signature to capture the unique compositional characteristics and systematic evolution of individual artist bodies of work, creation date time spans, and conventional style periods, while concepts of artist nationality remain problematic. Network analyses of individual artists and style periods clarify their rhizomatic confusion while uncovering three distinguished yet nonintuitive supergroups that are meaningfully clustered in time.

Quantitative social science. A network framework of cultural history.

The emergent processes driving cultural history are a product of complex interactions among large numbers of individuals, determined by difficult-to-quantify historical conditions. To characterize these processes, we have reconstructed aggregate intellectual mobility over two millennia through the birth and death locations of more than 150,000 notable individuals. The tools of network and complexity theory were then used to identify characteristic statistical patterns and determine the cultural and historical relevance of deviations. The resulting network of locations provides a macroscopic perspective of cultural history, which helps us to retrace cultural narratives of Europe and North America using large-scale visualization and quantitative dynamical tools and to derive historical trends of cultural centers beyond the scope of specific events or narrow time intervals.

Dynamics of ranking processes in complex systems.

The world is addicted to ranking: everything, from the reputation of scientists, journals, and universities to purchasing decisions is driven by measured or perceived differences between them. Here, we analyze empirical data capturing real time ranking in a number of systems, helping to identify the universal characteristics of ranking dynamics. We develop a continuum theory that not only predicts the stability of the ranking process, but shows that a noise-induced phase transition is at the heart of the observed differences in ranking regimes. The key parameters of the continuum theory can be explicitly measured from data, allowing us to predict and experimentally document the existence of three phases that govern ranking stability.