Date of Submission
Spring 2018
Academic Programs and Concentrations
Computer Science; Experimental Humanities
Project Advisor 1
Sven Anderson
Abstract/Artist's Statement
The purpose of this project is to identify subtweets. The Oxford English Dictionary defines "subtweet" as a "[Twitter post] that refers to a particular user without directly mentioning them, typically as a form of furtive mockery or criticism." This paper details a process for gathering a labeled ground truth dataset, training a classifier, and creating a Twitter bot which interacts with subtweets in real time. The Naive Bayes classifier trained in this project classifies tweets as subtweets and non-subtweets with an average F1 score of 72%.
Open Access Agreement
Open Access
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Recommended Citation
Segal-Gould, Noah L., "Don't Take This Personally: Sentiment Analysis for Identification of "Subtweeting" on Twitter" (2018). Senior Projects Spring 2018. 244.
https://digitalcommons.bard.edu/senproj_s2018/244
This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.