Writing for the Public: Immigration Discourse and Language Ideology
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Panagiotis Fytas.
In this talk, I will present some recent methodological and substantive work in text-based computational social science. To begin, I will present work on the history of immigration discourse in American political speech over the past 150 years, emphasizing aspects of tone, framing, and metaphor. Next, I will present a paper from EMNLP 2022 on the role of language ideology in data curation, specifically with respect to the question of text quality. Finally, time permitting, I will briefly discuss practical approaches to dealing with domain shift in text classification, especially when working with lexicons or otherwise inaccessible models (e.g., commercial APIs).
This talk is part of the Language Technology Lab Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|