Using NLP to Build a Sarcasm Classifier

In this article we will try to write a classifier for defining sarcastic articles using machine learning and TensorFlow.

The article is a translation from Machine Learning Foundations: Part 10 - Using NLP to build a sarcasm classifier

Rishab Mishra 's Sarcasm in News Headlines dataset is used as the training dataset . It's an interesting dataset that collects news headlines from conventional news sources, as well as a few more comedic ones from fake news sites.

The dataset is a JSON file with three columns.

• is_sarcastic  - 1 if the entry is sarcastic, otherwise 0
• headline - article title
• article_link - URL of the article text

We'll just look at headers here. So we have a very simple dataset to work with. The header is our feature, and is_sarcastic is our shortcut.

The JSON data looks something like this.

{
    "article_link": "https://www.huffingtonpost.com/entry/versace-black-code_us_5861fbefe4b0de3a08f600d5",
    "headline": "former versace store clerk sues over secret 'black code' for minority shoppers",
    "is_sarcastic": 0
}

Each record is a JSON field with name-value pairs showing the column and associated data.

Here is the code to load data in Python

import json

with open("sarcasm.json", 'r') as f:
    datastore = json.load(f)
sentences = [] 
labels = []
urls = []
for item in datastore:
    sentences.append(item['headline'])
    labels.append(item['is_sarcastic'])
    urls.append(item['article_link'])

. -, import json json Python. sarcasm.json. json.load(), . , URL-. .   , URL- .

.

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
tokenizer = Tokenizer(oov_token="")
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index
print(len(word_index))
print(word_index)
sequences = tokenizer.texts_to_sequences(sentences)
padded = pad_sequences(sequences, padding='post')
print(padded[0])
print(padded.shape)

. 25 000 , .   word_index . .

... 'blowing': 4064, 'packed': 4065, 'deficit': 4066, 'essential': 4067, 'explaining': 4068, 'pollution': 4069, 'braces': 4070, 'protester': 4071, 'uncle': 4072 ...

, , . , , , . 

[  308 15115   679  3337  2298    48   382  2576 15116     6  2577  8434
     0     0     0     0     0     0     0     0     0     0     0     0
     0     0     0     0     0     0     0     0     0     0     0     0
     0     0     0     0]
(26709, 40)

. , .  26 709 , 40 .

, .

voiceab_size = 10000 
embedding_dim = 16 
max_length = 100 
trunc_type = 'post' 
padding_type = 'post' 
oov_tok = "" 
training_size = 20000

26 000 20 000 , training_size, 6000 .

training_sentences = sentences[0:training_size]
testing_sentences = sentences[training_size:]
training_labels = labels[0:training_size]
testing_labels = labels[training_size:]

, , , , .

tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(training_sentences)

word_index = tokenizer.word_index

training_sequences = tokenizer.texts_to_sequences(training_sentences)
training_padded = pad_sequences(training_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

testing_sequences = tokenizer.texts_to_sequences(testing_sentences)
testing_padded = pad_sequences(testing_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

, , .  training_sentence.  .  test_sentences , . training_sequences training_sentences. , . testing_sentences .

, , , . — , , . , . .

, «Bad» «Good». , . , .

«meh» , . .

«not bad», , «Good», , . , .

, .  .

,   .

, Keras, Embedding.

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.Dense(24, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])

Embedding . , , , . 16, . , Embedding 10 016 , . , , .

, .

num_epochs = 30
history = model.fit(training_padded, training_labels, epochs=num_epochs, validation_data=(testing_padded, testing_labels), verbose=2)

training_padded, .

,   Google Colab, .