Nihal D'Souza
commited on
Commit
•
d8d6c9f
1
Parent(s):
9d994ae
Updating README with yaml metadata
Browse files
README.md
CHANGED
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
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.
|
2 |
Some of these models hindered the performance of He et al’s model, while others improved it.
|
3 |
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
tags:
|
4 |
+
- transfer-learning
|
5 |
+
- bert
|
6 |
+
- hatespeech
|
7 |
+
- covid19
|
8 |
+
license: "MIT License"
|
9 |
+
datasets:
|
10 |
+
- COVID-HATE
|
11 |
+
metrics:
|
12 |
+
- f1-score
|
13 |
+
---
|
14 |
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.
|
15 |
Some of these models hindered the performance of He et al’s model, while others improved it.
|
16 |
|