conviette commited on
Commit
afc7f7c
·
1 Parent(s): cf69c19

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -7
README.md CHANGED
@@ -1,14 +1,22 @@
1
- # korPolBERT
2
 
3
- This model is a BERT classification model to classify Korean user generated comments into binary labels of liberal or conservative.
4
- This model was trained on approximately 37,000 user generated comments collected from NAVER\'s news portal.
5
 
6
- This model is a finetuned model based on ETRI\'s KorBERT; the vocabulary file for the tokenizer should be obtained from ETRI.
 
 
7
 
 
 
8
 
 
 
 
 
 
 
 
 
 
 
9
 
10
 
11
 
12
- ---
13
- license: apache-2.0
14
- ---
 
 
1
 
 
 
2
 
3
+ ---
4
+ license: apache-2.0
5
+ ---
6
 
7
+ This model was developed to analyze comment authorship patterns on Korean news articles.
8
+ For further details, refer to our paper on Journalism: [News comment sections and online echo chambers: The ideological alignment between partisan news stories and their user comments](https://journals.sagepub.com/doi/full/10.1177/14648849211069241)
9
 
10
+ * This model is a BERT classification model to classify Korean user generated comments into binary labels of liberal or conservative.
11
+ * This model was trained on approximately 37,000 user generated comments collected from NAVER\'s news portal. The dataset was collected in 2019; as such, note that comments related to recent political topics might not be classified correctly.
12
+ * This model is a finetuned model based on ETRI\'s KorBERT.
13
+
14
+
15
+ ### Model performance
16
+
17
+ * Accuracy: 0.8322
18
+ * F1-Score: 0.8322
19
+ * For further technical details on the model, refer to our paper for the W-NUT workshop (EMNLP 2019), [The Fallacy of Echo Chambers: Analyzing the Political Slants of User-Generated News Comments in Korean Media](https://aclanthology.org/D19-5548/).
20
 
21
 
22