Back to search
Georgia Southern University
Determining Political Inclination in Tweets Using Transfer Learning
Abstract
dc:description.abstractLast few years have seen tremendous development in neural language modeling for transfer learning and downstream applications. In this research, I used Howard and Ruder’s Universal Language Model Fine Tuning (ULMFiT) pipeline to develop a classifier that can determine whether a tweet is politically left leaning or right leaning by likening the content to tweets posted by @TheDemocrats or @GOP accounts on Twitter. We achieved 87.7% accuracy in predicting political ideological inclination.
Degree
thesis:*- Name thesis:degree_name
- Master of Science, Information Technology
- Level thesis:degree_level
- Thesis (open access)
- Discipline thesis:degree_discipline
- Department of Information Technology
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Iqbal, Mehtab
- Contributors dc:contributor
-
- Cheryl Aasheim
- Christopher Kadlec
Subjects
dc:subject × 9Rights
- Licence dc:rights.license
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.georgiasouthern.edu/etd/1988