The Cultural Computation Lab applies computational methods to questions of culture. The lab focuses on the creation, curation, analysis, and visualization of corpora containing cultural or humanistic data. The application of computational methods to cultural data is inherently interdisciplinary requiring understanding and collaboration across many different fields.
Large corpora of cultural data are becoming increasing available to researchers. These new data sets come from many different sources including governmental open-data initiatives, academic projects, privately maintained but publicly available databases like Google Books, and from the efforts of on-line communities. Open source tools are also making it increasingly easy to create and host new collections.
Fortunately, this explosion of cultural data is coupled with increases in computational power and algorithmic techniques which permit its analysis. Cultural and humanistic datasets are often less structured than traditional “big data.” Cultural data often requires natural language processing techniques, in the case of textual data, or even computer vision and audio processing when examining collections of images, sound, and/or video.
The lab is training small cohorts of undergraduate students from Smith College and the University of Massachusetts in techniques needed for cultural computing using the Global Proverbs Project as an initial driver project. The Global Proverbs Project is an online, community supported, multilingual database of proverb’s currently under development.
Computer Science, Smith College
Robert A. Rothstein
Comparative Literature, UMass—Amherst