Detecting Fake News

In this article we will cover :

• What is Python?
• What is Fake News?
• The source code.
• Resources.

What is the Python Programming Language?

Python Programming language is an interpreted, object-oriented, high-level programming language with dynamic semantics, supporting modules and packages, which encourages program modularity and code reuse. It has the ability to create CSV output for easy data reading in a spreadsheet which alternatively more complicated file outputs that can be ingested by machine learning clusters for computation.

What is Fake News?

Fake News is Junk news or pseudo News, which usually contains disinformation, intended for misleading information for a particular topic that may contain fabricated headlines to increase readership.

The Source Code:

• Install libraries with pip

  pip install numpy pandas sklearn​

• First import the important imports:

  import numpy as np
  import pandas as pd
  import itertools​

• After that import from sklearn

  from sklearn.model_selection import train_test_split
  from sklearn.metrics import accuracy_score, confusion_matrix
  from sklearn.feature_extraction.text import TfidfVectorizer
  from sklearn.linear_model import PassiveAggressiveClassifier​

• Read the data from the dataset

  #Read the data
  df=pd.read_csv('C:\\DataSet\\newsdataset.csv')
  ​

• Shape and read your dataset and understand

  df.shape
  df.head(10)​

• Get the labels from DataFrame from the dataset

  labels=df.label
  labels.head()​

• Split Dataset into training and testing sets

  x_train,x_test,y_train,y_test=train_test_split(df['text'], labels, test_size=0.2, random_state=7)​

• fit and transform the vectorizer on the train set, and transform the vectorizer

  tfidf_vectorizer=TfidfVectorizer(stop_words='english', max_df=0.7)
  
  tfidf_train=tfidf_vectorizer.fit_transform(x_train) 
  tfidf_test=tfidf_vectorizer.transform(x_test)​

• Initialize the Passive-Aggressive Classifier

  pac=PassiveAggressiveClassifier(max_iter=50)
  pac.fit(tfidf_train,y_train)
  y_pred=pac.predict(tfidf_test)
  score=accuracy_score(y_test,y_pred)
  print(f'Accuracy: {round(score*100,2)}%')​

• Apply Confusion Matrix to gain insights

  confusion_matrix(y_test,y_pred, labels=['FAKE','REAL'])​

Resources

• https://www.python.org/
• https://datascience.berkeley.edu/about/what-is-data-science