tburst commited on
Commit
056f873
1 Parent(s): 1747264

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +72 -1
README.md CHANGED
@@ -3,7 +3,7 @@ license: mit
3
  ---
4
  ## Model description
5
 
6
- An xlm-roberta-large model fine-tuned on all ~1,8 million annotated statements contained in the [manifesto corpus](https://manifesto-project.wzb.eu/information/documents/corpus) (version 2023a).
7
  The model can be used to categorize any type of text into 56 different political topics according to the Manifesto Project's coding scheme ([Handbook 4](https://manifesto-project.wzb.eu/coding_schemes/mp_v4)).
8
 
9
  The context model variant additionally incorporates the surrounding sentences of a statement to improve the classification results for ambiguous sentences.
@@ -50,4 +50,75 @@ print(predicted_class)
50
  # 201 - Freedom and Human Rights
51
  ```
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
 
3
  ---
4
  ## Model description
5
 
6
+ An xlm-roberta-large model fine-tuned on ~1,6 million annotated statements contained in the [manifesto corpus](https://manifesto-project.wzb.eu/information/documents/corpus) (version 2023a).
7
  The model can be used to categorize any type of text into 56 different political topics according to the Manifesto Project's coding scheme ([Handbook 4](https://manifesto-project.wzb.eu/coding_schemes/mp_v4)).
8
 
9
  The context model variant additionally incorporates the surrounding sentences of a statement to improve the classification results for ambiguous sentences.
 
50
  # 201 - Freedom and Human Rights
51
  ```
52
 
53
+ ## Model Performance
54
+
55
+ The model was evaluated on a test set of 186,276 annotated manifesto statements (10% of the whole corpus).
56
+
57
+ ### Overall
58
+
59
+
60
+ | Accuracy | Top2_Acc | Top3_Acc | Precision| Recall | F1_Macro | MCC | Cross-Entropy |
61
+ |:--------:|:--------:|:--------:|:--------:|:------:|:--------:|:---:|:-------------:|
62
+ | 0.64 | 0.81 | 0.88 | 0.54 | 0.52 | 0.53 | 0.62| 1.15 |
63
+
64
+ ### Categories
65
+
66
+ |Category|Precision|Recall|F1|n_test(%)|n_predicted(%)|
67
+ |:------|:-----------:|:----:|:----:|:-----:|:-----:|
68
+ | 101 |0.50|0.48|0.49|0.30%|0.29%|
69
+ |102|0.56|0.61|0.58|0.09%|0.10%|
70
+ |103|0.51|0.36|0.42|0.28%|0.20%|
71
+ |104|0.78|0.81|0.79|1.57%|1.64%|
72
+ |105|0.69|0.70|0.69|0.34%|0.34%|
73
+ |106|0.59|0.57|0.58|0.33%|0.32%|
74
+ |107|0.68|0.66|0.67|2.24%|2.17%|
75
+ |108|0.66|0.68|0.67|1.20%|1.24%|
76
+ |109|0.52|0.39|0.45|0.17%|0.13%|
77
+ |110|0.63|0.68|0.65|0.36%|0.38%|
78
+ |201|0.58|0.59|0.59|2.16%|2.20%|
79
+ |202|0.62|0.63|0.62|3.25%|3.28%|
80
+ |203|0.46|0.47|0.47|0.19%|0.19%|
81
+ |204|0.61|0.37|0.46|0.25%|0.15%|
82
+ |301|0.66|0.71|0.68|2.13%|2.29%|
83
+ |302|0.38|0.25|0.30|0.17%|0.11%|
84
+ |303|0.58|0.60|0.59|5.12%|5.31%|
85
+ |304|0.67|0.65|0.66|1.38%|1.34%|
86
+ |305|0.59|0.57|0.58|2.32%|2.22%|
87
+ |401|0.45|0.36|0.40|1.50%|1.21%|
88
+ |402|0.61|0.58|0.59|2.73%|2.60%|
89
+ |403|0.56|0.51|0.53|3.59%|3.25%|
90
+ |404|0.30|0.15|0.20|0.58%|0.28%|
91
+ |405|0.43|0.51|0.47|0.18%|0.21%|
92
+ |406|0.38|0.46|0.42|0.26%|0.31%|
93
+ |407|0.56|0.52|0.54|0.40%|0.38%|
94
+ |408|0.28|0.17|0.21|1.34%|0.79%|
95
+ |409|0.37|0.21|0.27|0.24%|0.14%|
96
+ |410|0.53|0.50|0.52|2.22%|2.08%|
97
+ |411|0.73|0.75|0.74|8.32%|8.53%|
98
+ |412|0.26|0.20|0.22|0.58%|0.45%|
99
+ |413|0.49|0.63|0.55|0.29%|0.37%|
100
+ |414|0.58|0.55|0.56|1.38%|1.32%|
101
+ |415|0.14|0.23|0.18|0.05%|0.07%|
102
+ |416|0.52|0.49|0.50|2.45%|2.35%|
103
+ |501|0.69|0.78|0.73|4.77%|5.35%|
104
+ |502|0.78|0.84|0.81|3.08%|3.32%|
105
+ |503|0.61|0.63|0.62|5.96%|6.11%|
106
+ |504|0.71|0.76|0.74|10.05%|10.76%|
107
+ |505|0.46|0.37|0.41|0.69%|0.55%|
108
+ |506|0.78|0.82|0.80|5.42%|5.72%|
109
+ |507|0.45|0.26|0.33|0.14%|0.08%|
110
+ |601|0.52|0.46|0.49|1.79%|1.57%|
111
+ |602|0.35|0.34|0.34|0.24%|0.24%|
112
+ |603|0.65|0.68|0.67|1.36%|1.42%|
113
+ |604|0.62|0.48|0.54|0.57%|0.44%|
114
+ |605|0.72|0.74|0.73|4.22%|4.33%|
115
+ |606|0.56|0.48|0.51|1.45%|1.23%|
116
+ |607|0.57|0.67|0.62|1.08%|1.25%|
117
+ |608|0.48|0.48|0.48|0.41%|0.41%|
118
+ |701|0.62|0.66|0.64|3.35%|3.59%|
119
+ |702|0.42|0.30|0.35|0.08%|0.06%|
120
+ |703|0.75|0.87|0.80|2.65%|3.07%|
121
+ |704|0.43|0.32|0.37|0.57%|0.43%|
122
+ |705|0.38|0.33|0.35|0.80%|0.69%|
123
+ |706|0.43|0.37|0.39|1.35%|1.16%|
124