poltextlab commited on
Commit
20fbdf8
1 Parent(s): 90341ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -34,6 +34,18 @@ The model can be used as any other (cased) BERT model. It has been tested recogn
34
 
35
  Fine-tuned version of the original huBERT model (`SZTAKI-HLT/hubert-base-cc`), trained on HunEmPoli corpus.
36
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  ## Eval results
38
 
39
  | Class | Precision | Recall | F-Score |
 
34
 
35
  Fine-tuned version of the original huBERT model (`SZTAKI-HLT/hubert-base-cc`), trained on HunEmPoli corpus.
36
 
37
+ | Category | Count | Ratio | Sentiment | Count | Ratio |
38
+ | -------- | ----- | ------ | --------- | ----- | ------ |
39
+ | Neutral | 351 | 1.85% | Neutral | 351 | 1.85% |
40
+ | Fear | 162 | 0.85% | Negative | 11180 | 58.84% |
41
+ | Sadness | 4258 | 22.41% |
42
+ | Anger | 643 | 3.38% |
43
+ | Disgust | 6117 | 32.19% |
44
+ | Success | 6602 | 34.74% | Positive | 7471 | 39.32% |
45
+ | Joy | 441 | 2.32% |
46
+ | Trust | 428 | 2.25% |
47
+ | Sum | 19002 | | | | |
48
+
49
  ## Eval results
50
 
51
  | Class | Precision | Recall | F-Score |