Multi Class Text Classification using CNN and word2vec

Multi Class Classification is not just Positive or Negative emotions it can have a range of outcomes [1,2,3,4,5,6…n]

Anakin

2 min readDec 30, 2020

Filtering comments for obscene and bad language before posting

Online Bullying

Understanding Sentiments

Identifying angry customers and offering timely service

Many More

Imports

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.layers import Dense, Input, GlobalMaxPooling1D
from keras.layers import Conv1D, MaxPooling1D, Embedding
from keras.models import Model
from sklearn.metrics import roc_auc_score

Word2vec Dict : Using glove.6B/glove.6B

word2vec = {}
with open(os.path.join('glove.6B/glove.6B.%sd.txt' % EMBEDDING_DIM)) as f:
  # is just a space-separated text file in the format:
  # word vec[0] vec[1] vec[2] ...
  for line in f:
    values = line.split()
    word = values[0]
    vec = np.asarray(values[1:], dtype='float32')
    word2vec[word] = vec
print('Found %s word vectors.' % len(word2vec))

Tokenize the Train Set

tokenizer = Tokenizer(num_words=MAX_VOCAB_SIZE)
tokenizer.fit_on_texts(sentences)
sequences = tokenizer.texts_to_sequences(sentences)

Create the Embedding Matrix

num_words = min(MAX_VOCAB_SIZE, len(word2idx) + 1)
embedding_matrix = np.zeros((num_words, EMBEDDING_DIM))
for word, i in word2idx.items():
  if i < MAX_VOCAB_SIZE:
    embedding_vector = word2vec.get(word)
    if embedding_vector is not None:
      # words not found in embedding index will be all zeros.
      embedding_matrix[i] = embedding_vector

CNN Model

input_ = Input(shape=(MAX_SEQUENCE_LENGTH,))
x = embedding_layer(input_)
x = Conv1D(128, 3, activation='relu')(x)
x = MaxPooling1D(3)(x)
x = Conv1D(128, 3, activation='relu')(x)
x = MaxPooling1D(3)(x)
x = Conv1D(128, 3, activation='relu')(x)
x = GlobalMaxPooling1D()(x)
x = Dense(128, activation='relu')(x)
output = Dense(len(possible_labels), activation='sigmoid')(x)

model = Model(input_, output)
model.compile(
  loss='binary_crossentropy',
  optimizer='rmsprop',
  metrics=['accuracy']
)

print('Training model...')
r = model.fit(
  data,
  targets,
  batch_size=BATCH_SIZE,
  epochs=EPOCHS,
  validation_split=VALIDATION_SPLIT
)