NSF-NRT Interdisciplinary Training in Complex Networks and Systems
Friday, Feb 26th 2021 at 11:30 A.M.
https://iu.zoom.us/j/571267563
This talk is part of the NSF-NRT Interdisciplinary Training in Complex Networks and Systems. Find the full event details here.
Where: https://iu.zoom.us/j/571267563
Title: Leveraging the Alignment between Machine Learning and Intersectionality: Using Word Embeddings to Measure Intersectional Experiences of the Nineteenth Century U.S. South
Abstract: Machine learning is a rapidly growing research paradigm. Despite its foundationally inductive mathematical assumptions, the machine learning paradigm is currently developing alongside inferential statistics but largely orthogonally to inductive, cultural, and intersectional research - to its detriment. I argue that we can better realize the full potential of machine learning by leveraging the epistemological alignment between machine learning and intersectional, cultural, and inductive research. I empirically demonstrate this alignment through a word embedding model of first-person narratives of the nineteenth-century U.S. South. Situating social categories in relation to social institutions via an inductive computational analysis, I find that the cultural and economic spheres discursively distinguished by race in these narratives, the domestic sphere distinguished by gender, and Black men were afforded more discursive authority compared to white women. Even in a corpus over-representing abolitionist sentiment, white identities were afforded a status via culture not allowed Black identities.
Bio: Dr. Nelson uses computational tools, principally automated text analysis, to study social movements, culture, gender, institutions, and organizations. She has a particular interest in applying these tools with a qualitative lens, and to better understand intersectionality and inequality. Dr. Nelson is an open source and open science enthusiast and seeks to use open-source tools and computational methods to make the social sciences and humanities more transparent, reproducible, and scalable.