Update README.md

README.md

@@ -106,7 +106,7 @@ def testing_data_prep(text):
     # Removing stopwords, such as do, not, as, etc. (https://gist.github.com/sebleier/554280)
     new_filtered_words = [
     word for word in words if word not in stopwords.words('english')]
-    if 12 >= len(new_filtered_words) >= 6:
+    if 20 >= len(new_filtered_words) >= 6:
       return ' '.join(new_filtered_words)
     return ' '
 ```
@@ -131,6 +131,7 @@ The following hyperparameters were used during training:
 https://huggingface.co/datasets/GonzaloA/fake_news
 https://github.com/GeorgeMcIntire/fake_real_news_dataset
 https://onlineacademiccommunity.uvic.ca/isot/2022/11/27/fake-news-detection-datasets/
+https://www.kaggle.com/datasets/saurabhshahane/fake-news-classification/data
 
 
 #### Metrics
@@ -152,14 +153,15 @@ weighted avg       0.94      0.94      0.94      8117
 
 For testing on https://github.com/GeorgeMcIntire/fake_real_news_dataset
 ```
-              precision    recall  f1-score   support
+               precision    recall  f1-score   support
+
+           0       0.93      0.88      0.90      2297
+           1       0.89      0.93      0.91      2297
 
-           0       0.81      0.87      0.84      2297
-           1       0.86      0.80      0.83      2297
+    accuracy                           0.91      4594
+   macro avg       0.91      0.91      0.91      4594
+weighted avg       0.91      0.91      0.91      4594
 
-    accuracy                           0.83      4594
-   macro avg       0.83      0.83      0.83      4594
-weighted avg       0.83      0.83      0.83      4594
 ```
 For testing on https://onlineacademiccommunity.uvic.ca/isot/2022/11/27/fake-news-detection-datasets/
 ```
@@ -173,6 +175,17 @@ For testing on https://onlineacademiccommunity.uvic.ca/isot/2022/11/27/fake-news
 weighted avg     0.9731    0.9731    0.9731     19996
 ```
 
+For testing on random 1k rows of https://www.kaggle.com/datasets/saurabhshahane/fake-news-classification/data
+```
+              precision    recall  f1-score   support
+
+           0       0.87      0.80      0.84       492
+           1       0.82      0.89      0.85       508
+
+    accuracy                           0.85      1000
+   macro avg       0.85      0.85      0.85      1000
+weighted avg       0.85      0.85      0.85      1000
+```
 #### Hardware
 
 Tesla T4 GPU, available for free in Google Collab