Data-driven methods are becoming more and more important in Humanities. Fundamental.
Digital tools have been producing a huge increase in the amount of data, in forms that only computers can process. A point has been reached where manual analyses of the data by individual researchers or even groups of researchers are impractical. This is due not just to the huge amounts of data but also to its heterogeneous and complex nature. As a consequence, it is necessary to develop automatic, computer-based methods to process, analyze, and visualize the data.
How can data science help to better understand / interpret data from Humanities? How can new theories be developed? Is it possible to produce empirically-grounded predictions about the future? What are the impacts for the research and the society? What are the business opportunities? These are some of the possible themes and challenges of a data-driven approach in Humanities.
New techniques, resources, challenges, and developments in the area come from the interface between pure/applied sciences and Humanities. Relevant topics combine pure and applied sciences (such as maths, stats, physics, engineering, computer science) with Humanities’ subjects (e.g. anthropology, archaeology, jurisprudence, philosophy, psychology, history, linguistics, literature), in order to develop new and effective techniques, tools, insights.
In this facebook group, and in this linkedin group, we share and discuss the application of data-driven methods to Humanities, we try to map the sectors where digital data are currently used, processed, and analyzed.
Topics include application of Artificial Intelligence to Art, digital curation of data from Humanities, big data in Archaeology, algorithms to detect plagiarism, natural language understanding, experimental Philosophy, Geography, Social Science research data. Important issues deal with a right understanding of the statistics behind the data analysis, metadata, open data (read this interesting article on Why Scientits must share their research code? )
It is very important to point out that data-driven approaches must be a fruitful combination of expertise and experiences of people coming from different backgrounds: no mathematician will ever be an archaeologist, and no archaeologist will never be a mathematician. It’s the big picture that matters.