English | EN Looking at Culture through a Big Data Lens
Dec 12, 2013
I’m excited about all the (possible) breakthroughs we see happening in cultural research. For instance identifying trends in the work of artist by using Big Data visual analysis, analyzing narratives to predict Times Person of the Year and looking at twitter feeds to gain better understanding of human well being. These examples and research projects show that there’s a lot going on in this very diversified field of cultural research.
Global Pulse Twitter analyses
One of the great examples is the United Nations Global Pulse project. The Global Pulse initiative is exploring how new, digital data sources and real-time analytics technologies can help policymakers understand human well-being and emerging vulnerabilities in real-time, in order to better protect populations from shocks.
The initiative was established based on recognizing that digital data offers the opportunity to gain a better understanding of changes in human well being, and to get real-time feedback on how well policy responses are working. The overarching objective of Global Pulse is to mainstream the use of data mining and real-time data analytics into development organizations and communities of practice. One example of Global Pulse Research comes from their Lab in Indonesia. They have built a model to predict real-time inflation rates bases on Tweets. As you can see Twitter is quite popular in Jakarta.
Left: Map of Jakarta based on Tweets. Right: Real-time inflation based on text analysis.
The inflation rate is based on text-analyses of the words used on twitter. A combination of certain words used, like for instance “minyak goreng” – cooking oil and “ketahanan pangan” – food security – result in a .89 correlation with inflation.
Predicting by looking at narratives
Other Big Data cultural research examples will be presented tomorrow at a conference organized by the Dutch Meertens Institute “Patterns in narrative texts“. The data that will be discussed range from narrative journalistic texts to orally transmitted folktales. In the study of history, diachronic corpora can be mined to discover how historical events are reflected in language use. In folk narrative research, patterns of interest include the stability and variability of ‘narrative building blocks’ (motifs, memes) in oral transmission, and geographical dispersion of folk beliefs in the supernatural. Establishing links between narrative texts is a common factor in all this research.
One of the pieces of research that will be discussed is “Mining the Twentieth Century’s History from the TIME Magazine Corpus”. Mike Kestemont & Folgert Karsdorp are going to explain how to predict Times’s Person of the Year. In their research they have paid special attention to the intriguing interplay between this list of influential personalities and the manner in which they are discussed in the magazine’s own archive. They will have a lot to explain, looking at their top-10 list for 2013, since they’ve missed the person that has won this year, Pope Fransicus. But still the researchers have a hit-rate of more than 20%.
Person of The Year 2013 prediction
1: Barack Obama
2: Vladimir Putin
3: Miley Cyrus
4: George W. Bush
5: Angelina Jolie
6: Katie Couric
7: David Bowie
8: Rush Limbaugh
9: John Kerry
10: Hamid Karzai
Seeing paintings as data
How about looking paintings as esthetic objects and as data. By doing that you can identifying outliers, trends in painters work, typical images, seeing them statistically and historically. Lev Manovich looked at paintngs from Mark Rothko, using interactive visualization on 287 megapixel HIPerSpace visual supercomputer. Manovich current research is focused on cultural analytics – the use of computational methods for the analysis of massive cultural data sets and flows. At Software Studies Initiative he is working on a particular part of analytics paradigm – using digital image analysis and visualization for working with large visual collections. How we do analyze millions of digitized visual artifacts from the past? How do we explore billions of digital photos and videos (both user-generated content and professional media)? How do we research interactive media processes and experiences (evolution of web design, playing a video game)?
About the author
