Quantifying the development of user-generated art during 2001–2010

Abstract

One of the main questions in the humanities is how cultures and artistic expressions change over time. While a number of researchers have used quantitative computational methods to study historical changes in literature, music, and cinema, our paper offers the first quantitative analysis of historical changes in visual art created by users of a social online network. We propose a number of computational methods for the analysis of temporal development of art images. We then apply these methods to a sample of 270,000 artworks created between 2001 and 2010 by users of the largest social network for art—DeviantArt (www.deviantart.com). We investigate changes in subjects, techniques, sizes, proportions and also selected visual characteristics of images. Because these artworks are classified by their creators into two general categories—Traditional Art and Digital Art—we are also able to investigate if the use of digital tools has had a significant effect on the content and form of artworks. Our analysis reveals a number of gradual and systematic changes over a ten-year period in artworks belonging to both categories.

History of art paintings through the lens of entropy and complexity

“…Among other findings, they have observed a sudden increase in the diversity of color contrast after 1850, and showed also that the same quantity can be used to capture information about artistic styles. Notably, there is also innovative research done by Manovich and coworkers (41)(42)(43) concerning the analysis of large-scale datasets…”

Researching Culture through Big Data: Computational Engineering and the Human and Social Sciences

“…An example of this is DeviantArt, one of the objects studied by 'cultural analytics' (Yazdani et al 2017). DeviantArt is described as a digital platform "for emerging and established artists to exhibit, promote, and share their works with an enthusiastic, art-centric community" 5 .…”

“…Each section contains an assessment of the possibilities and the limitations detected in these approaches, all of which have a common interest in quantifying social facts. In order to illustrate this counterpoint more clearly, several concrete examples are offered: the study, characteristic of the 'distant reading' method, of the representation of how London developed, drawing on about 5000 English novels published between 1700 and 1900 (Heuser et al 2016); an analysis of a million works of art disseminated between 2001 and 2010 on the digital platform DeviantArt, in the categories 'Traditional Art' and 'Digital Art' (Yazdani et al 2017); and the first cultural indicators from the EU using big data, based on millions of views of Wikipedia pages on cultural heritage. The conclusion offers an overall view of the different sections of the article, bringing them together for a considered, integrated view of the scope and limitations of the linkages between the study of culture in the human and social sciences by means of big data and its ties to computational engineering.…”

Dissecting landscape art history with information theory

“…Understanding how artistic expressions and design principles have changed over time is a central question in art history, aesthetics, and cultural evolution ( 1 – 7 ) as individual artists reflected aesthetic values through their artworks, while aggregate notions of zeitgeist remain theoretically contested. In visual art, an artist often determines the main compositional characteristics of an artwork through an interplay of nonexplicit latent variables that are often imperfectly summarized in categorical concepts, including visual elements, such as the formalist notions of line, shape, tone, color, pattern, texture, form, etc.…”

“…Computational assessments of visual art so far contributed to characterize diverse statistical properties of paintings such as the fractal dimension, the Fourier power spectrum, and frequency distributions in color space ( 17 – 21 ). Moreover, recent statistical analyses have been applied to quantify the evolution of artistic style and representation ( 3 – 7 , 22 – 25 ), to authenticate and estimate creation dates ( 26 – 28 ); to reproduce characterizing styles of specific artists ( 29 ), and to classify the systematic novelty of artists ( 30 ). Moreover, beyond the characterization of artworks, art historical metadata including exhibition trajectories and auction price history shed new light on the dynamics behind the careers of artists ( 31 – 33 ).…”