Scribd
Upload
104 views8 pages

Fake News Detection with LSTM

This document contains the code for a fake news detection application. It uses natural language processing techniques like cleaning, tokenization, and TF-IDF to preprocess text data. It then trains an LSTM neural network model to classify news articles as genuine or fake. The code provides functions for uploading and preprocessing data, running the LSTM algorithm, viewing training accuracy and loss graphs, and testing the model on new data. A GUI is created using Tkinter to allow users to interact with the various functions of the application.

Uploaded by

Dudhipala Deepak Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
104 views8 pages

Fake News Detection with LSTM

This document contains the code for a fake news detection application. It uses natural language processing techniques like cleaning, tokenization, and TF-IDF to preprocess text data. It then trains an LSTM neural network model to classify news articles as genuine or fake. The code provides functions for uploading and preprocessing data, running the LSTM algorithm, viewing training accuracy and loss graphs, and testing the model on new data. A GUI is created using Tkinter to allow users to interact with the various functions of the application.

Uploaded by

Dudhipala Deepak Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

SAMPLE CODE

[Link]

from tkinter import messagebox


from tkinter import *
from tkinter import simpledialog
import tkinter
import [Link] as plt
import numpy as np
from tkinter import ttk
from tkinter import filedialog
import pandas as pd
from sklearn.model_selection import train_test_split
from string import punctuation
from [Link] import stopwords
import nltk
from [Link] import WordNetLemmatizer
from sklearn.feature_extraction.text import TfidfVectorizer
from [Link] import LabelEncoder
from [Link] import Sequential
from [Link] import Dense,Activation,Dropout
from [Link] import OneHotEncoder
import [Link]
from [Link] import model_from_json
import pickle
import os
from [Link] import normalize

from [Link] import Sequential


from [Link] import Dense, Dropout, Flatten, LSTM

main = Tk()
[Link]("DETECTION OF FAKE NEWS THROUGH
IMPLEMENTATION OF DATA SCIENCE APPLICATION")
[Link]("1300x1200")
global filename
global X, Y
global tfidf_X_train, tfidf_X_test, tfidf_y_train, tfidf_y_test
global tfidf_vectorizer
global accuracy,error

stop_words = set([Link]('english'))
lemmatizer = WordNetLemmatizer()

textdata = []
labels = []
global classifier

def cleanPost(doc):
tokens = [Link]()
table = [Link]('', '', punctuation)
tokens = [[Link](table) for w in tokens]
tokens = [word for word in tokens if [Link]()]
tokens = [w for w in tokens if not w in stop_words]
tokens = [word for word in tokens if len(word) > 1]
tokens = [[Link](token) for token in tokens]
tokens = ' '.join(tokens)
return tokens

def uploadDataset():
global filename
[Link]('1.0', END)
filename =
[Link](initialdir="TwitterNewsData")
[Link]()
[Link]()
dataset = pd.read_csv(filename)
dataset = [Link](' ')
for i in range(len(dataset)):
msg = dataset.get_value(i, 'text')
label = dataset.get_value(i, 'target')
msg = str(msg)
msg = [Link]().lower()
[Link](int(label))
clean = cleanPost(msg)
[Link](clean)
[Link](END,clean+" ==== "+str(label)+"\n")

def preprocess():
[Link]('1.0', END)
global X, Y
global tfidf_vectorizer
global tfidf_X_train, tfidf_X_test, tfidf_y_train, tfidf_y_test
stopwords=stopwords = [Link]("english")
tfidf_vectorizer = TfidfVectorizer(stop_words=stopwords,
use_idf=True, ngram_range=(1,2),smooth_idf=False, norm=None,
decode_error='replace', max_features=200)
tfidf = tfidf_vectorizer.fit_transform(textdata).toarray()
df = [Link](tfidf,
columns=tfidf_vectorizer.get_feature_names())
[Link](END,str(df))
print([Link])
df = [Link]
X = df[:, 0:[Link][1]]
X = normalize(X)
Y = [Link](labels)
le = LabelEncoder()
Y = le.fit_transform(Y)
indices = [Link]([Link][0])
[Link](indices)
X = X[indices]
Y = Y[indices]
Y = [Link](-1, 1)
print([Link])
encoder = OneHotEncoder(sparse=False)
#Y = encoder.fit_transform(Y)
X = [Link](([Link][0], [Link][1], 1))
print(Y)
print([Link])
print([Link])
tfidf_X_train, tfidf_X_test, tfidf_y_train, tfidf_y_test =
train_test_split(X, Y, test_size=0.2)
[Link](END,"\n\nTotal News found in dataset : "+str(len(X))
+"\n")
[Link](END,"Total records used to train machine learning
algorithms : "+str(len(tfidf_X_train))+"\n")
[Link](END,"Total records used to test machine learning
algorithms : "+str(len(tfidf_X_test))+"\n")

def runLSTM():
[Link]('1.0', END)
global classifier
if [Link]('model/[Link]'):
with open('model/[Link]', "r") as json_file:
loaded_model_json = json_file.read()
classifier = model_from_json(loaded_model_json)
classifier.load_weights("model/model_weights.h5")
classifier._make_predict_function()
print([Link]())
f = open('model/[Link]', 'rb')
data = [Link](f)
[Link]()
acc = data['accuracy']
acc = acc[9] * 100
[Link](END,"LSTM Fake News Detection Accuracy :
"+str(acc)+"\n\n")
[Link](END,'LSTM Model Summary can be seen in black
console for layer details\n')
with open('model/[Link]', 'rb') as file:
classifier = [Link](file)
[Link]()
else:
lstm_model = Sequential()
lstm_model.add(LSTM(128, input_shape=([Link][1:]),
activation='relu', return_sequences=True))
lstm_model.add(Dropout(0.2))

lstm_model.add(LSTM(128, activation='relu'))
lstm_model.add(Dropout(0.2))

lstm_model.add(Dense(32, activation='relu'))
lstm_model.add(Dropout(0.2))

lstm_model.add(Dense(2, activation='softmax'))
lstm_model.compile(loss='sparse_categorical_crossentropy',
optimizer='adam', metrics=['accuracy'])
hist = lstm_model.fit(X, Y, epochs=10,
validation_data=(tfidf_X_test, tfidf_y_test))
classifier = lstm_model
classifier.save_weights('model/model_weights.h5')
model_json = classifier.to_json()
with open("model/[Link]", "w") as json_file:
json_file.write(model_json)
accuracy = [Link]
f = open('model/[Link]', 'wb')
[Link](accuracy, f)
[Link]()
acc = accuracy['accuracy']
acc = acc[9] * 100
[Link](END,"LSTM Accuracy : "+str(acc)+"\n\n")
[Link](END,'LSTM Model Summary can be seen in black
console for layer details\n')
print(lstm_model.summary())

def graph():
f = open('model/[Link]', 'rb')
data = [Link](f)
[Link]()
acc = data['accuracy']
loss = data['loss']
[Link](figsize=(10,6))
[Link](True)
[Link]('Epcchs')
[Link]('Accuracy/Loss')
[Link](acc, 'ro-', color = 'green')
[Link](loss, 'ro-', color = 'blue')
[Link](['Accuracy','Loss'], loc='upper left')
#[Link]([Link])
[Link]('LSTM Model Accuracy & Loss Graph')
[Link]()

def predict():
testfile =
[Link](initialdir="TwitterNewsData")
testData = pd.read_csv(testfile)
[Link]('1.0', END)
testData = [Link]
testData = testData[:,0]
print(testData)
for i in range(len(testData)):
msg = testData[i]
msg1 = testData[i]
print(msg)
review = [Link]()
review = [Link]().lower()
review = cleanPost(review)
testReview = tfidf_vectorizer.transform([review]).toarray()
predict = [Link](testReview)
print(predict)
if predict == 0:
[Link](END,msg1+" === Given news predicted as
GENUINE\n\n")
else:
[Link](END,msg1+" == Given news predicted as FAKE\
n\n")

font = ('times', 15, 'bold')


title = Label(main, text='DETECTION OF FAKE NEWS
THROUGH IMPLEMENTATION OF DATA SCIENCE
APPLICATION')
[Link](bg='gold2', fg='thistle1')
[Link](font=font)
[Link](height=3, width=120)
[Link](x=0,y=5)

font1 = ('times', 13, 'bold')


ff = ('times', 12, 'bold')

uploadButton = Button(main, text="Upload Fake News Dataset",


command=uploadDataset)
[Link](x=20,y=100)
[Link](font=ff)
processButton = Button(main, text="Preprocess Dataset",
command=preprocess)
[Link](x=20,y=150)
[Link](font=ff)

dtButton = Button(main, text="Run LSTM Algorithm",


command=runLSTM)
[Link](x=20,y=200)
[Link](font=ff)

graphButton = Button(main, text="Accuracy & Loss Graph",


command=graph)
[Link](x=20,y=250)
[Link](font=ff)

predictButton = Button(main, text="Test News Detection",


command=predict)
[Link](x=20,y=300)
[Link](font=ff)

font1 = ('times', 12, 'bold')


text=Text(main,height=30,width=100)
scroll=Scrollbar(text)
[Link](yscrollcommand=[Link])
[Link](x=330,y=100)
[Link](font=font1)

[Link](bg='DarkSlateGray1')
[Link]()

You might also like