luerhard commited on
Commit
be9509d
·
1 Parent(s): 6a44566

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -11
README.md CHANGED
@@ -10,18 +10,27 @@ pipeline_tag: text-classification
10
  inital commit
11
 
12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  # Performance
14
 
15
- This table presents the classification report for a 5-fold
16
- cross-validation of our model. The hyperparameters are consistent
17
- across all 5 runs. The final and published model was then trained on
18
- all data with the same hyperparameters. It is evident that the model
19
- performs, on average, best for anti-elitism but performs the worst for
20
- the detection of right-wing host ideology. The relatively small
21
- standard deviations suggest that the split into training and test data
22
- has minimal impact on model performance. Therefore, it is expected
23
- that the performance of the final model will be comparable to what is
24
- depicted here.
25
 
26
  | Dimension | Precision | Recall | F1 |
27
  |---------------------|---------------|---------------|---------------|
@@ -29,6 +38,6 @@ This table presents the classification report for a 5-fold
29
  | People-Centrism | 0.670 (0.011) | 0.725 (0.040) | 0.696 (0.019) |
30
  | Left-Wing Ideology | 0.664 (0.023) | 0.771 (0.024) | 0.713 (0.010) |
31
  | Right-Wing Ideology | 0.654 (0.029) | 0.698 (0.050) | 0.674 (0.031) |
32
- | | | | |
33
  | micro avg | 0.732 (0.009) | 0.805 (0.006) | 0.767 (0.007) |
34
  | macro avg | 0.700 (0.011) | 0.770 (0.010) | 0.733 (0.010) |
 
10
  inital commit
11
 
12
 
13
+ # Prediction
14
+
15
+ The model outputs a Tensor of length 4.
16
+ The table connects the position of the predicted probability to its dimension.
17
+
18
+ | **Index** | **Dimension** |
19
+ |-----------|--------------------------|
20
+ | 0 | Anti-Elitism |
21
+ | 1 | People-Centrism |
22
+ | 2 | Left-Wing Host-Ideology |
23
+ | 3 | Right-Wing Host-Ideology |
24
+
25
+
26
  # Performance
27
 
28
+ This table presents the classification report for a 5-fold cross-validation of our model.
29
+ The hyperparameters are consistent across all 5 runs. The final and published model was then trained on all data with the same hyperparameters.
30
+ It is evident that the model performs, on average, best for anti-elitism but performs the worst for detecting right-wing host ideology.
31
+ The relatively small standard deviations suggest that the split into training and test data has minimal impact on model performance.
32
+ Therefore, it is expected that the performance of the final model will be comparable to what is
33
+ depicted here.
 
 
 
 
34
 
35
  | Dimension | Precision | Recall | F1 |
36
  |---------------------|---------------|---------------|---------------|
 
38
  | People-Centrism | 0.670 (0.011) | 0.725 (0.040) | 0.696 (0.019) |
39
  | Left-Wing Ideology | 0.664 (0.023) | 0.771 (0.024) | 0.713 (0.010) |
40
  | Right-Wing Ideology | 0.654 (0.029) | 0.698 (0.050) | 0.674 (0.031) |
41
+ | --- | --- | --- | --- |
42
  | micro avg | 0.732 (0.009) | 0.805 (0.006) | 0.767 (0.007) |
43
  | macro avg | 0.700 (0.011) | 0.770 (0.010) | 0.733 (0.010) |