Skip to content

COVID-19 Anti-Asian Racism Hate Speech Detection using Transfer Learning

License

Notifications You must be signed in to change notification settings

nihaldsouza/covid-hatespeech-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

COVID-19 Anti-Asian Racism Hate Speech Detection using Transfer Learning

Since the start of the COVID-19 pandemic, there has been a widespread increase in the amount of hate-speech being propagated online against the Asian community. This project builds upon and explores the work of He et al. Their COVID-HATE dataset contains 206 million tweets focused around anti-Asian hate speech. Using tweet data from before the COVID-19 pandemic, as well as the COVID-HATE dataset from He et al, we performed transfer learning. We tested several different models, including BERT, RoBERTa, LSTM, and BERT-CNN.
Some of these models hindered the performance of He et al’s model, while others improved it.

You can access the original proposal here: Proposal

You can access the full report here: Report

We also explored the geographical extent of the ani-Asain tweets from the COVID-HATE dataset.

global

Since a large majority of the tweets originated from U.S.A., here is a map showing the distribution within this country.

usa

Releases

No releases published

Packages

No packages published