Tracking Immigration Discourse on Twitter Using NLP

Social media is a major driver of political thought, with platforms like Facebook, Twitter,
and TikTok having a massive impact on how people think and vote. For this reason we should
take seriously any large shifts in the language used to describe issues or groups on social
media, as these are likely to either denote a change in political thought or even forecast the
same.
Of particular interest, given the international reach of social media, is the way that
discussions around foreign relations and immigration play out. In the United States of America
online spaces have become the default space for the ongoing discourse around immigration
policy and more generally the home of both pro and anti-immigrant activists. Because of the
sheer size of social media however, understanding how this discussion actually plays out is very
difficult, and being able to meaningfully track changes in the way individuals talk about
immigration is even more so.
Computational techniques, especially those developed by the subfield of Natural
Language Processing (NLP) may be able to fill this gap, and I have spent the last two terms
testing various methods for identifying changes in the language used on twitter when discussing
immigration. This work has centered around the social media environment of the 2016
Presidential election, which featured bitter arguments around immigration policy. The result of
my experimentation has been the ability to discover, under certain conditions, changes in the
most important terminology used to discuss immigration as well the identification of what may be
a generally useful technique for tracking language change on social media for any subject
matter.