Data Mining and Learning Analytics

CHAPTER 2ON BIG DATA AND TEXT MINING IN THE HUMANITIES

Geoffrey Rockwell¹ and Bettina Berendt²

¹ Philosophy and Humanities Computing, University of Alberta (KIAS), Edmonton, Alberta, Canada

² Department of Computer Science, University of Leuven, Leuven, Belgium

The analysis of texts has been central to humanists since at least the Renaissance. Italian humanists like Lorenzo Valla developed critical practices of interpretation and textual analysis as they tried to recover and interpret the classical texts of Greece and Rome (Nauta 2013; Valla 1985). The Renaissance humanism of writers like Petrarch, Machiavelli, and Valla was a reaction against pedantic scholasticism and returned attention to human language and literature—to the texts themselves. Humanists renewed our interest in human expression, especially the literary, historical, and philosophical classics. They started traditions of discovering and teaching our cultural record through the ongoing reading of texts, traditions still central to the humanities and, for that matter, the modern school system.¹

Now humanists are experimenting with text mining to study the large collections of literary and historical texts made available by projects like Google Books. To understand how the humanities are adopting text analysis and mining techniques, this paper will look at a history of selected projects that expanded our view of how information technology can be used in textual studies and developed models for the infrastructure ...