diff --git a/dev-0/naive_bigram.pkl b/dev-0/naive_bigram.pkl
index 65b8291..8aeb34f 100644
Binary files a/dev-0/naive_bigram.pkl and b/dev-0/naive_bigram.pkl differ
diff --git a/dev-0/out.tsv b/dev-0/out.tsv
index d2c2dda..3201db3 100644
--- a/dev-0/out.tsv
+++ b/dev-0/out.tsv
@@ -116,7 +116,7 @@
  P
  S
  S
- P
+ S
  S
  P
  P
@@ -1850,7 +1850,7 @@
  S
  S
  S
- P
+ S
  S
  S
  S
@@ -2511,7 +2511,7 @@
  P
  P
  P
- P
+ S
  P
  S
  S
@@ -2788,7 +2788,7 @@
  S
  S
  P
- P
+ S
  S
  S
  P
@@ -2924,7 +2924,7 @@
  S
  P
  S
- P
+ S
  P
  S
  S
@@ -3521,7 +3521,7 @@
  S
  S
  S
- P
+ S
  S
  S
  S
diff --git a/predict.py b/predict.py
index 0ed14e7..547d64e 100755
--- a/predict.py
+++ b/predict.py
@@ -30,11 +30,11 @@ def calc_post_class(post, paranormal_class_logprob, sceptic_class_logprob, bigra
 
 def clear_post(post):
     post = post.replace('\\n', ' ')
-    post = re.sub(r'(\(|)(http|https|www)[a-zA-Z0-9\.\:\/\_\=\&\;\-\?\+]+(\)|)', '', post)
-    post = re.sub(r'[\.\,]+', ' ', post)
-    post = re.sub(r'(&lt|&gt)','',post) 
-    post = re.sub(r'[\'\(\)\?\*\"\`\;0-9\[\]\:\%]+', '', post)
-    post = re.sub(r' \- ', ' ', post) 
+    post = re.sub(r'(\(|)(http|https|www)[a-zA-Z0-9\.\:\/\_\=\&\;\-\?\+\%]+(\)|)', '', post)
+    post = re.sub(r'[\.\,\/\~]+', ' ', post)
+    post = re.sub(r'(&lt|&gt|\@[a-zA-Z0-9]+)','',post) 
+    post = re.sub(r'[\'\(\)\?\*\"\`\;0-9\[\]\:\%\|]+', '', post)
+    post = re.sub(r'( \- |\-\-+)', ' ', post) 
     post = re.sub(r' +', ' ', post)
     post = post.rstrip(' ')
     return post
diff --git a/test-A/out.tsv b/test-A/out.tsv
index 5c4fe57..e9dedc1 100644
--- a/test-A/out.tsv
+++ b/test-A/out.tsv
@@ -235,7 +235,7 @@
  S
  S
  S
- P
+ S
  S
  S
  S
@@ -343,7 +343,7 @@
  P
  S
  S
- P
+ S
  S
  S
  S
@@ -357,7 +357,7 @@
  P
  S
  S
- P
+ S
  P
  S
  S
@@ -425,7 +425,7 @@
  S
  P
  S
- S
+ P
  S
  S
  S
@@ -441,7 +441,7 @@
  P
  S
  S
- P
+ S
  S
  P
  P
@@ -456,7 +456,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
@@ -694,7 +694,7 @@
  S
  P
  S
- S
+ P
  S
  P
  S
@@ -844,7 +844,7 @@
  S
  P
  S
- S
+ P
  S
  P
  S
@@ -998,7 +998,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
@@ -1268,7 +1268,7 @@
  P
  S
  S
- P
+ S
  S
  S
  P
@@ -1383,7 +1383,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
@@ -1582,7 +1582,7 @@
  S
  S
  S
- P
+ S
  S
  S
  S
@@ -1788,7 +1788,7 @@
  S
  S
  P
- S
+ P
  S
  S
  S
@@ -1855,7 +1855,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
@@ -1986,7 +1986,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
@@ -2217,7 +2217,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
@@ -2227,7 +2227,7 @@
  S
  S
  S
- P
+ S
  S
  S
  S
@@ -3282,7 +3282,7 @@
  S
  P
  S
- S
+ P
  S
  S
  S
@@ -3378,7 +3378,7 @@
  S
  S
  P
- S
+ P
  S
  S
  P
@@ -3724,7 +3724,7 @@
  S
  P
  S
- P
+ S
  S
  S
  S
@@ -3765,7 +3765,7 @@
  P
  S
  S
- P
+ S
  S
  S
  S
@@ -4111,7 +4111,7 @@
  P
  S
  P
- P
+ S
  S
  S
  S
@@ -4190,7 +4190,7 @@
  S
  S
  S
- P
+ S
  P
  S
  P
@@ -4344,7 +4344,7 @@
  S
  S
  S
- S
+ P
  P
  S
  S
@@ -4421,19 +4421,19 @@
  S
  P
  P
- P
  S
  S
  S
  S
  S
- P
  S
  P
  S
+ P
  S
  S
  S
+ P
  S
  S
  S
@@ -4763,7 +4763,7 @@
  S
  S
  S
- S
+ P
  S
  S
  S
diff --git a/train.py b/train.py
index d9ea143..7384838 100755
--- a/train.py
+++ b/train.py
@@ -25,11 +25,11 @@ def calc_class_logprob(expected_path):
 def clear_post(post):
     post = post.replace('\\n', ' ')
     # delete links
-    post = re.sub(r'(\(|)(http|https|www)[a-zA-Z0-9\.\:\/\_\=\&\;\?\+]+(\)|)', '', post)
-    post = re.sub(r'[\.\,\/]+', ' ', post)
-    post = re.sub(r'(&lt|&gt)','',post)
-    post = re.sub(r'[\'\(\)\?\*\"\`\;0-9\[\]\:\%]+', '', post)
-    post = re.sub(r' \- ', ' ', post)
+    post = re.sub(r'(\(|)(http|https|www)[a-zA-Z0-9\.\:\/\_\=\&\;\?\+\-\%]+(\)|)', '', post)
+    post = re.sub(r'[\.\,\/\~]+', ' ', post)
+    post = re.sub(r'(&lt|&gt|\@[a-zA-Z0-9]+)','',post)
+    post = re.sub(r'[\'\(\)\?\*\"\`\;0-9\[\]\:\%\|]+', '', post)
+    post = re.sub(r'( \- |\-\-+)', ' ', post)
     post = re.sub(r' +', ' ', post)
     post = post.rstrip(' ')
     return post
@@ -45,7 +45,7 @@ def calc_bigram_count(in_path, expected_path):
             for index in range(len(tokens)-1):
                 # if there is next token we append current and next
                 bigram = tokens[index] + " " + tokens[index + 1]
-                #print(bigram)
+                print(bigram)
                 #print (f"bigram constructed from ;;;;{tokens[index]}:{tokens[index+1]};;;;;;;")
                 if class_ == 'P':
                     bigram_counts['paranormal'][bigram] +=1