Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
RoBERTa model for detecting framing elements in tweets related to social movements.
|
| 2 |
+
|
| 3 |
+
Multilabel classification of 7 categories:
|
| 4 |
+
|
| 5 |
+
- problem identification (diagnostic core framing task)
|
| 6 |
+
- blame attribution (diagnostic core framing task)
|
| 7 |
+
- proposing solutions (prognostic core framing task)
|
| 8 |
+
- discussing tactics (prognostic core framing task)
|
| 9 |
+
- expressing solidarity / celebrating a movement (prognostic core framing task)
|
| 10 |
+
- counterframing / challenging the opposite sides' arguments (prognostic core framing task)
|
| 11 |
+
- motivational / calls to action (motivational core framing task)
|
| 12 |
+
|
| 13 |
+
The model is trained on Twitter data from three issue areas: guns, LGBTQ rights, and immigration.
|
| 14 |
+
All data is in English and written in 2018-2019.
|
| 15 |
+
|
| 16 |
+
Paper: https://journalqd.org/article/view/5896
|