Dangerous Art of Text Mining

A Methodology for Digital History

Inbunden, Engelska, 2023

Av Jo Guldi

1 679 kr

Beställningsvara. Skickas inom 3-6 vardagar

Fri frakt för medlemmar vid köp för minst 249 kr.

Finns i fler format (1)

Häftad

619 kr

Skickas inom 3-6 vardagar

The Dangerous Art of Text Mining celebrates the bold new research now possible because of text mining: the art of counting words over time. However, this book also presents a warning: without help from the humanities, data science can distort the past and lead to perilous errors. The book opens with a rogue's gallery of errors, then tours the ground-breaking analyses that have resulted from collaborations between humanists and data scientists. Jo Guldi explores how text mining can give a glimpse of the changing history of the past - for example, how quickly Americans forgot the history of slavery. Textual data can even prove who was responsible in Congress for silencing environmentalism over recent decades. The book ends with an impassioned vision of what text mining in defence of democracy would look like, and why humanists need to be involved.

Produktinformation

Utgivningsdatum2023-10-05
Mått152 x 229 x 27 mm
Vikt0 g
FormatInbunden
SpråkEngelska
Antal sidor436
FörlagCambridge University Press
ISBN9781009262989

Tillhör följande kategorier

Historia: teori och metod inom Historia och arkeologi

Introduction; Part I. A Ropes Course for Exploring the Territory: 1. Why textual data from the past is dangerous; 2. From fantasy to engagement; 3. Words are keys and words are barriers; 4. Critical search, a theory; 5. To predict or to describe?; Part II. The Many Windows of the House of the Past: 6. The many windows of the house of the past; 7. Of memory; 8. The distinctiveness of certain eras; 9. The measure of influence; 10. Of rock and fire; 11. Whither modernity; 12. What computers can explain and when to stop: a case study in the political history of climate change; Part III. Critical Thinking with Data Makes Stronger Disciplines: 13. A world map of culture, purged of bias; 14. The future of the art.

'An ambitious work that demonstrates how quantitative methods can inform the study of the past while also making a compelling case for how historical methods should inform the work of data science. Guldi outlines a middle ground based on “hybrid thinking,” where historians and data scientists can meet to think critically about how data is used and abused to understand the past and present.' Spencer Dean Stewart, H-Net