diff --git a/Fake_News_Detector_Improved.ipynb b/Fake_News_Detector_Improved.ipynb
new file mode 100644
index 0000000..dbe7c65
--- /dev/null
+++ b/Fake_News_Detector_Improved.ipynb
@@ -0,0 +1,647 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "b6edf3ba",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import re\n",
+ "import pickle\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+ "from sklearn.naive_bayes import MultinomialNB\n",
+ "from sklearn.metrics import accuracy_score, confusion_matrix\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "a8b8f15a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def preprocess(text):\n",
+ " text = text.lower()\n",
+ " text = re.sub(r'\\W', ' ', text)\n",
+ " text = re.sub(r'\\s+', ' ', text)\n",
+ " return text.strip()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "cb9f81aa",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Load datasets\n",
+ "true = pd.read_csv('data/True.csv')\n",
+ "fake = pd.read_csv('data/Fake.csv')\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "610f29ba",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Add labels\n",
+ "true['label'] = 1\n",
+ "fake['label'] = 0\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "e5bd1bae",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Preprocess\n",
+ "true['text'] = true['text'].apply(preprocess)\n",
+ "fake['text'] = fake['text'].apply(preprocess)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "7013c671",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Balance dataset\n",
+ "min_len = min(len(true), len(fake))\n",
+ "true = true.sample(min_len, random_state=42)\n",
+ "fake = fake.sample(min_len, random_state=42)\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "90325fb1",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Combine and shuffle\n",
+ "df = pd.concat([true, fake])\n",
+ "df = df.sample(frac=1, random_state=42).reset_index(drop=True)\n",
+ "\n",
+ "X = df['text']\n",
+ "y = df['label']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "2565508c",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+ "\n",
+ "# Improved vectorizer settings\n",
+ "vectorizer = TfidfVectorizer(stop_words='english', max_df=0.9, min_df=2, ngram_range=(1,2))\n",
+ "X_train_vec = vectorizer.fit_transform(X_train)\n",
+ "X_test_vec = vectorizer.transform(X_test)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "2fdcccc5",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "MultinomialNB()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.