RENEW 2013: The 5th International Conference on the Histories of Media Art, Science and Technology
Keynote lecture by Lev Manovich
Riga (Latvia), 7:00 pm, October 11, 2013.
Looking at one million images:
How visualization of big cultural data helps us to question our cultural categories.
The explosive growth of cultural content on the web including social media since 2004 and the digitization efforts by museums, libraries, and other institutions make possible a new paradigm for the study of both contemporary and historical media. Rather than only focusing on isolated artifacts, we can use computational data analysis and visualization techniques to study the patterns in massive cultural data sets.
Many interesting projects that follow on this idea have already been carried out by people in computer scientists, digital humanities, and artistic visualization field. But many important questions still remain. For example, how can we do explore massive visual collections of user-generated content containing billions of images? What new theoretical concepts do we need to deal with scale of born-digital culture? How do we use data mining of massive cultural data sets to question our cultural assumptions and biases, and "unlearn" what we know?
In my talk I will address these questions using examples from my Software Studies Lab (softwarestudies.com) established in 2007. I will briefly present the techniques we developed for exploratory analysis of massive visual collections, and show examples of our projects including analysis of 1 million pages from Manga books, 1 million user-generated artworks (from deviantart.com), and 2.3 million Instagram photos. I will also discuss how computational analysis and visualization of big cultural data sets leads us to question traditional discrete categories used for cultural categorization such as "style" and "period."