using positive and negative test files now and fixed demographic

recent_add_labels.py

 import json
 import chardet
 
+positive_words = set()
+negative_words = set()
+
+# Read positive words from the file "positive.txt"
+with open("positive.txt", 'r', encoding='utf-8') as positive_file:
+    positive_words.update(word.strip().casefold() for word in positive_file)
+
+# Read negative words from the file "negative.txt"
+with open("negative.txt", 'r', encoding='utf-8') as negative_file:
+    negative_words.update(word.strip().casefold() for word in negative_file)
+
 json_data = {
     "projectFileVersion": "2022-05-01",
     "stringIndexType": "Utf16CodeUnit",
@@ -49,13 +60,15 @@ for i in range(1, 11):
             ]
         }
         for ind, word in enumerate(utf_data.split()):
-            if word.casefold().__contains__("positive") or word.casefold().__contains__("excite") or word.casefold().__contains__("benefit") or word.casefold().__contains__("beneficial") or word.casefold().__contains__("favor") or word.casefold().__contains__("good") or word.casefold().__contains__("optimist") or word.casefold().__contains__("favor"):
+            #if word.casefold().__contains__("positive") or word.casefold().__contains__("excite") or word.casefold().__contains__("benefit") or word.casefold().__contains__("beneficial") or word.casefold().__contains__("favor") or word.casefold().__contains__("good") or word.casefold().__contains__("optimist") or word.casefold().__contains__("favor"):
+            if word.casefold() in positive_words:  
                 category = "positive"
                 offset = utf_data.find(word, last_position)
                 length = len(word)
                 last_position = offset + length
                 is_a_category = True
-            elif word.casefold().__contains__("negative") or word.casefold().__contains__("concern") or word.casefold().__contains__("harm") or word.casefold().__contains__("reject") or word.casefold().__contains__("oppose") or word.casefold().__contains__("danger") or word.casefold().__contains__("bad") or word.casefold().__contains__("pessimist") or word.casefold().__contains__("risk") or word.casefold().__contains__("threat"):
+            #elif word.casefold().__contains__("negative") or word.casefold().__contains__("concern") or word.casefold().__contains__("harm") or word.casefold().__contains__("reject") or word.casefold().__contains__("oppose") or word.casefold().__contains__("danger") or word.casefold().__contains__("bad") or word.casefold().__contains__("pessimist") or word.casefold().__contains__("risk") or word.casefold().__contains__("threat"):
+            elif word.casefold() in negative_words:    
                 category = "negative"
                 offset = utf_data.find(word, last_position)
                 length = len(word)
@@ -67,7 +80,7 @@ for i in range(1, 11):
                 length = len(word)
                 last_position = offset + length
                 is_a_category = True
-            elif word.casefold().__contains__("American") or word.casefold().__contains__("white") or word.casefold().__contains__("black") or word.casefold().__contains__("asian") or word.casefold().__contains__("hispanic") or word.casefold().__contains__("women") or word.casefold().__contains__("men"):
+            elif word.casefold().__contains__("American") or word.casefold().__contains__("white") or word.casefold().__contains__("black") or word.casefold().__contains__("asian") or word.casefold().__contains__("hispanic") or word.casefold() == "women" or word.casefold() == "men":
                 category = "demographic"
                 offset = utf_data.find(word, last_position)
                 length = len(word)