Large-Scale Text Analysis

Fresh from digital humanities bootcamps this summer, three training grant recipients share their new-found DH knowledge. Penn grad students Tabea Cornel and Carolyn Fornoff explore what they've learned about large-scale text analysis and how they plan to implement it in their own research.

Tabea Cornel | "Finding Cerebral Sex/Gender Differences and Adult Neurogenesis with R: Mining Neuroscientific Publications from Five Decades"
Cornel will discuss her plans to use R to analyse neuroscientific papers from major neuroscientists who are credited with (re)discovering adult neurogenesis, a specific form of brain plasticity. These papers originate from endeavors in the 1960s to contemporary research. She is looking for data to help answer the following two questions: 1) When, if at all, did the specified researchers start using terms like "adult neurogenesis" or "plasticity" for their findings, i.e., did they "know" that they found what we are attributing to them today? 2) To what extent has research on sex/gender differences in the brain coincided with research on the malleability of brains in cerebral plasticity research, i.e., when, if at all, was a concept of gendered brains (male/female differences through experience) as opposed to sexed brains (female/male differences through genetics and pre-natal hormone exposure) possible?

Carolyn Fornoff | "Working with R: Applications and Limitations"
In this talk Fornoff addresses some of the applications and limitations that working with R entails for literary and cultural studies. She will discuss the accessibility of programming for humanities students unfamiliar with coding, the difficulty of preparing a corpus for large scale text analysis, and how languages other than English are searchable within R.