Critical Practice in Text Data Mining Research Cluster, 2020-2021 Project Report

Keralis, Spencer D. C.

Permalink

https://hdl.handle.net/2142/113441 Copy

Description

Title

Critical Practice in Text Data Mining Research Cluster, 2020-2021 Project Report

Author(s)

Keralis, Spencer D. C.

Contributor(s)

• Worthey, Glen
• Ton, Mary Borgo

Issue Date

2021-06-07

Keyword(s)

text mining, text data mining, algorithmic bias, digital archives, mass digitization

Abstract

Text data mining (TDM) is the computational and statistical analysis of large corpora of texts. Often positioned in a dialectical relationship with, if not in opposition to, the humanities methods of aesthetics and hermeneutics, text data mining is one of the cornerstone methodologies of the broad and idiosyncratic field known as digital humanities. As a field that is necessarily allied closely with the computer and information sciences, the digital humanities, and text mining in particular, are implicated if not complicit in the problems of bias; representation in terms of gender, race, and class; labor ethics; and other problems that are endemic in the tech industries. This research cluster proposes to examine how text data mining, as a disciplinarily diverse field, has manifested these problems, and how the University of Illinois digital scholarship community can work together to address them, moving toward a critical practice of text data mining that is ethical, just, and inclusive.

Type of Resource

text

Language

en

Permalink

http://hdl.handle.net/2142/113441

Sponsor(s)/Grant Number(s)

Humanities Research Institute

Copyright and License Information

CC-BY-NC-SA

Owning Collections