diff --git a/ekphrasis/classes/preprocessor.py b/ekphrasis/classes/preprocessor.py
index e79f171..fef6ab8 100644
--- a/ekphrasis/classes/preprocessor.py
+++ b/ekphrasis/classes/preprocessor.py
@@ -134,8 +134,8 @@ def handle_hashtag_match(self, m):
         text = m.group()[1:]
 
         # todo:simplify routine
+        expanded = self.segmenter.segment(text)
         if text.islower():
-            expanded = self.segmenter.segment(text)
             expanded = " ".join(expanded.split("-"))
             expanded = " ".join(expanded.split("_"))
             # print(m.group(), " - ", expanded)
@@ -145,7 +145,6 @@ def handle_hashtag_match(self, m):
 
         else:
             # split words following CamelCase convention
-            expanded = self.regexes["camel_split"].sub(r' \1', text)
             expanded = expanded.replace("-", "")
             expanded = expanded.replace("_", "")
             # print(m.group(), " - ", expanded)
diff --git a/ekphrasis/classes/segmenter.py b/ekphrasis/classes/segmenter.py
index 821de70..4bf579a 100644
--- a/ekphrasis/classes/segmenter.py
+++ b/ekphrasis/classes/segmenter.py
@@ -131,6 +131,8 @@ def find_segment(self, text, prev='<S>'):
     # if you don't have enough RAM lower the maxsize
     @lru_cache(maxsize=65536)
     def segment(self, word):
+        if word.isupper() or (word[0].isupper() and word[1:].islower()):
+            word = word.lower()
         if word.islower():
             return " ".join(self.find_segment(word)[1])
         else:
diff --git a/ekphrasis/tools/generate_stats.py b/ekphrasis/tools/generate_stats.py
index ba110f7..c521aa3 100644
--- a/ekphrasis/tools/generate_stats.py
+++ b/ekphrasis/tools/generate_stats.py
@@ -12,7 +12,7 @@
 import numpy
 from tqdm import tqdm
 
-REGEX_TOKEN = re.compile(r'(?<![#@])\b[a-z]{1,15}\b')
+REGEX_TOKEN = re.compile(r'(?<![#@])\b[a-z\u00C0-\u00FF0-9]{1,15}\b')
 REGEX_URL = re.compile(
     r"(https?:\/\/(?:www\.|(?!www))[^\s\.]+\.[^\s]{2,}|www\.[^\s]+\.[^\s]{2,})")
 SEPARATOR = "_"